Intelligent air sampler and sampler flow monitoring feedback control method

Abstract

The invention discloses an intelligent air sampler and a sampler flow monitoring feedback control method. The intelligent air sampler comprises a host sampler, a mobile terminal and a remote server, the host sampler is provided with a Bluetooth module or a GPRS (General Packet Radio Service) communication module; an APP application program is installed in the mobile terminal; the host sampler is used for collecting samples, caching data and sending the data to the mobile terminal through the Bluetooth module or the GPRS communication module; the mobile terminal is used for receiving data, storing the data, performing data operation and sending a control instruction to the host sampler; the mobile terminal is further used for obtaining first abnormal data information when judging that the current traffic data is smaller than the minimum traffic threshold value or larger than the maximum traffic threshold value or larger than the maximum traffic threshold value, and generating a traffic control instruction; and the remote server performs database analysis on the forwarded data to obtain second abnormal data information, and feeds back an optimization control instruction to the mobile terminal according to the second abnormal data information. According to the intelligent air sampler and the sampler flow monitoring feedback control method, real-time monitoring of the current sampler flow of a user is achieved, intelligent monitoring and feedback control can be provided for the current sampler, and therefore it is guaranteed that the sampling flow of the sampler is constant and stable; and stable and efficient work and remote cooperative control of the sampler are ensured. Meanwhile, monitoring data of the multiple intelligent air samplers can be monitored through the mobile terminal on the hand of each operator, and efficient management of monitoring the multiple air samplers at the same time through one person and one machine is achieved.

Description

Technical Field

[0001] The invention relates to sampling operations of dust and chemical substances in ambient air, and in particular to an intelligent air sampler and a sampler flow monitoring feedback control method. Background Art

[0002] Backpack air samplers (primarily used to collect samples of hazardous materials such as dust or chemicals) have become an important tool in the field of environmental monitoring and occupational safety through their portability, efficiency and versatility;

[0003] Research has found that the main function of a backpack air sampler is to collect harmful substances such as dust and chemicals in the ambient air. Its design makes it easy to carry and suitable for use in various working environments, such as workplaces such as mines and industrial plants. The backpack dust sampler mainly consists of a backpack structure, an air inlet pipe, a host sampler connected to the air inlet pipe (equipped with an efficient vacuum pump that can stably inhale air to ensure sufficient collection of dust samples) and an air outlet pipe; it supports different types of dust sampling (such as total dust, inhalable dust, PM2.5, PM10, etc.), which can be flexibly selected according to needs. The host sampler is equipped with a data recording function, which can monitor and record sampling data in real time for subsequent analysis.

[0004] However, further research revealed that the host sampler in the prior art may have abnormal sampling flow due to the blocked inlet pipe bends or even due to equipment abnormalities of the host sampler. However, when such abnormal flow occurs, the staff is often unaware of it and unable to detect the abnormality in time through monitoring means. The abnormal sampling flow seriously affects the judgment of the sampling results, thereby affecting the on-site sampling of harmful substances in the workplace air and the subsequent laboratory testing and inspection work. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent air sampler and a sampler flow monitoring feedback control method to solve the problem that the host sampler in the prior art cannot realize flow abnormality monitoring and feedback control.

[0006] In order to achieve the above technical purpose, the present invention adopts the following technical solution:

[0007] The present invention provides an intelligent air sampler, comprising a host sampler, a mobile terminal and a remote server:

[0008] Including host sampler, mobile terminal and remote server:

[0009] The host sampler is provided with a Bluetooth module or a GPRS communication module;

[0010] The mobile terminal is installed with an APP application;

[0011] The host sampler is used to collect samples, cache data and send the data to the mobile terminal via a Bluetooth module or a GPRS communication module;

[0012] The mobile terminal is used to receive data, store data, perform data operations, and send control instructions to the host sampler; the mobile terminal is also used to forward the received data to the remote server; the mobile terminal is used to obtain the first abnormal data information when it is determined that the current flow data is less than the minimum flow threshold or greater than the maximum flow threshold, and generate a flow control instruction; the generated flow control instruction is sent to the host sampler through a Bluetooth module or a GPRS communication module;

[0013] The remote server performs database analysis on the forwarded data to obtain second abnormal data information, and feeds back an optimization control instruction to the mobile terminal according to the second abnormal data information.

[0014] Preferably, as an implementable solution, the host sampler also includes: a flow sensor for real-time monitoring of the sampling flow; a processing unit for processing the data of the flow sensor to obtain the sampling data and flow data of the current sampling sample; the sampling data includes the dust composition of the current sampling sample; the flow data is the sampling volume; a storage unit for temporarily storing the sampling data and flow data; the processing unit sends the processed data to the mobile terminal via a Bluetooth module or a GPRS communication module.

[0015] Preferably, as an implementable embodiment, the APP application of the mobile terminal includes:

[0016] A data receiving module, used for receiving sampling data and flow data sent by the host sampler;

[0017] A data analysis module is used to analyze the received traffic data and determine whether the current traffic data is less than a minimum traffic threshold or greater than a maximum traffic threshold;

[0018] A flow control module, for generating a flow control instruction and obtaining first abnormal data information when judging that the current flow data is less than a minimum flow threshold or greater than a maximum flow threshold; the first abnormal data information includes an ID number of the current host sampler and the current host sampler flow;

[0019] The flow control module is used to send the generated flow control instruction to the host sampler through the Bluetooth module or the GPRS communication module.

[0020] Preferably, as an implementable solution, the remote server is connected to the mobile terminal via a network; and the mobile terminal uploads the sampling data and flow data to the remote server.

[0021] Preferably, as an implementable embodiment, the remote server further comprises:

[0022] Database, used to store historical sampling data and historical flow data;

[0023] A machine learning model module, used for analyzing historical sampling data and historical flow data to obtain a detection model, performing abnormality monitoring on currently acquired sampling data and flow data based on the detection model, and outputting second abnormal data information of the flow data;

[0024] The second abnormal data information includes the ID number of the current host sampler and the current host sampler flow.

[0025] Preferably, as an implementable solution, the data structure of the historical sampling data also includes: workplace, timestamp range, sample ID, dust composition; the data structure of the historical flow data includes flow data;

[0026] The machine learning model module specifically includes a first processing module and a second processing module; the first processing module is used to perform regression analysis training on the data structure of the historical sampling data and the data structure of the historical flow data when analyzing the historical sampling data and the historical flow data to obtain the detection model, and obtain a mapping relationship table between the dust composition and the flow data range threshold value in the current workplace in the target timestamp range segment;

[0027] The second processing module is an anomaly detection module; the second processing module is used to judge whether the current flow data significantly deviates from the mean of the historical flow data of the current workplace in the current timestamp range segment based on the real-time data of the dust composition and flow data in the current workplace in the current timestamp range segment (or time period); if the deviation value exceeds 15%, it is deemed to be a significant deviation and a second abnormal data information is sent.

[0028] Preferably, as an implementable embodiment, the APP application of the mobile terminal further includes:

[0029] A user interface module for displaying real-time sampling data and flow data;

[0030] An alarm module, configured to issue an alarm when second abnormal data information is detected;

[0031] The remote control module is used to accept the input instructions of the user through the user interface module and perform the operation of remotely adjusting the sampling parameters of the host sampler; the sampling parameters include increasing or decreasing the working speed of the sampling pump.

[0032] A sampler flow monitoring feedback control method, which uses an intelligent air sampler to perform flow monitoring feedback control operations, includes the following steps:

[0033] S10, the host sampler collects samples and monitors the current flow;

[0034] S20, the host sampler sends the sampling data and flow data to the mobile terminal via Bluetooth;

[0035] S30, the mobile terminal receives data, stores data, performs data operations, and sends control instructions to the host sampler; at the same time, the mobile terminal also forwards the received data to the remote server;

[0036] S40, when the mobile terminal determines that the current flow data is less than the minimum flow threshold or greater than the maximum flow threshold, the mobile terminal obtains the first abnormal data information and generates a flow control instruction; the generated flow control instruction is sent to the host sampler through the Bluetooth module or the GPRS communication module;

[0037] S50, the remote server performs a database analysis on the forwarded data to obtain second abnormal data information, and feeds back an optimization control instruction to the mobile terminal according to the second abnormal data information;

[0038] S60. The host sampler adjusts the sampling flow rate according to the received control instruction.

[0039] Preferably, as an implementable embodiment, step S50 specifically includes the following steps:

[0040] S51, the mobile terminal uploads the sampling data and flow data to the remote server;

[0041] S52, the remote server performs in-depth analysis on the data, detects abnormalities in the sampled data and sampled traffic, and obtains second abnormal data information;

[0042] S53: The remote server then feeds back an optimization control instruction to the mobile terminal according to the second abnormal data information.

[0043] Preferably, as an implementable embodiment, the deep analysis step of the remote server includes:

[0044] Perform regression analysis training on the data structure of historical sampling data and the data structure of historical flow data to obtain a mapping relationship table between dust components in the current workplace within the target timestamp range and flow data range thresholds;

[0045] Based on the real-time data of the dust composition and flow data of the current workplace in the current timestamp range, a judgment is made to determine whether the current flow data significantly deviates from the mean of the historical flow data of the current workplace in the current timestamp range; if the deviation value exceeds 15%, it is deemed to be a significant deviation and a second abnormal data information is sent.

[0046] Preferably, as an implementable embodiment, the method further comprises the following steps:

[0047] The mobile terminal displays sampling data and flow data in real time; when an alarm is issued when the second abnormal data information is detected, the mobile terminal issues an alarm; the user receives an operation of remotely adjusting the sampling parameters of the host sampler through the mobile terminal; the sampling parameters include increasing or decreasing the operating speed of the sampling pump.

[0048] Compared with the prior art, the embodiments of the present invention have at least the following technical advantages:

[0049] It can be known from the analysis of the above-mentioned intelligent air sampler and sampler flow monitoring feedback control method provided by the present invention that the intelligent air sampler can monitor the sampling flow in real time through the flow sensor and Bluetooth module or GPRS communication module in the host sampler to ensure the continuity and stability of the sampling process. At the same time, the APP of the mobile terminal can receive and process data in real time for data analysis, and then timely determine whether the flow is less than the minimum flow threshold or greater than the maximum flow threshold, and detect abnormal flow; when it is confirmed that the flow is abnormal, the corresponding control instruction is generated to ensure that the sampling flow is maintained within the optimal range.

[0050] The above-mentioned mobile terminal is installed with an APP application; the APP application communicates with the Bluetooth module or the GPRS communication module to implement a method for sampler flow monitoring and feedback control, which realizes the implementation monitoring of the user's current sampler flow. The APP application can provide intelligent monitoring and feedback control for the current sampler, thereby ensuring the constant and stable sampling flow of the sampler, ensuring the stable and efficient operation of the sampler and remote collaborative control; at the same time, the APP application can also directly accept the user's operation instructions and directly adjust the working parameters of the sampler; in addition, the core control logic processing also includes a remote server, which performs an in-depth analysis of historical data to timely detect abnormal working conditions of the host sampler, and feedbacks optimization control instructions to the mobile terminal, and finally the mobile terminal controls the host sampler to execute the operation of the entire sampler's working parameters; therefore, the flow adjustment of the host sampler includes at least three control methods, which realizes automatic early warning and intelligent intervention of abnormal conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a schematic diagram of the structural principle of an intelligent air sampler;

[0052] Figure 2 It is a schematic diagram of the specific structural principle of a host sampler in an intelligent air sampler;

[0053] Figure 3 A schematic diagram of the specific structural principle of an APP application in a smart air sampler;

[0054] Figure 4 A schematic diagram of the specific structural principle of a remote server in an intelligent air sampler;

[0055] Figure 5 It is a main flow diagram of a sampler flow monitoring feedback control method;

[0056] Figure 6 The present invention is a schematic diagram of a specific operation flow of a sampler flow monitoring feedback control method.

[0057] Label:

[0058] Intelligent air sampler 100;

[0059] Host sampler 10; Bluetooth module or GPRS communication module 11; flow sensor 12; processing unit 13; storage unit 14;

[0060] Mobile terminal 20; APP application 21; data receiving module 211; data analysis module 212; flow control module 213; said flow control module 214;

[0061] Remote server 30: database 31; machine learning model module 32. DETAILED DESCRIPTION

[0062] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] The present invention is further described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0064] The embodiment of the present invention provides an intelligent air sampler and a sampler flow monitoring feedback control method.

[0065] The principle structure of the intelligent air sampler of this embodiment is first described below; Figure 1 As shown, in the first aspect, an embodiment of the present invention provides an intelligent air sampler 100, including a host sampler 10, a mobile terminal 20 and a remote server 30:

[0066] The host sampler 10 is provided with a Bluetooth module or a GPRS communication module 11;

[0067] The mobile terminal 20 is installed with an APP application 21;

[0068] The host sampler 10 is used to collect samples, cache data and send the data to the mobile terminal via a Bluetooth module or a GPRS communication module;

[0069] The mobile terminal 20 is used to receive data, store data, perform data operations, and send control instructions to the host sampler; the mobile terminal is also used to forward the received data to the remote server; the mobile terminal is used to obtain the first abnormal data information when it is determined that the current flow data is less than the minimum flow threshold or greater than the maximum flow threshold, and generate a flow control instruction; the generated flow control instruction is sent to the host sampler through the Bluetooth module or the GPRS communication module;

[0070] The remote server 30 performs database analysis on the forwarded data to obtain second abnormal data information, and feeds back an optimization control instruction to the mobile terminal according to the second abnormal data information.

[0071] It should be noted that the above-mentioned mobile terminal is installed with an APP application; the APP application communicates with the Bluetooth module or the GPRS communication module to implement a method for sampler flow monitoring and feedback control, which realizes the implementation monitoring of the user's current sampler flow, and the APP application can provide intelligent monitoring and feedback control for the current sampler, thereby ensuring the constant and stable sampling flow of the sampler, ensuring the stable and efficient operation of the sampler and remote collaborative control; at the same time, the APP application can also directly accept the user's operation instructions and directly adjust the working parameters of the sampler; in addition, the core control logic processing also includes a remote server, which performs an in-depth analysis of historical data to detect abnormal working conditions of the host sampler in a timely manner, and feeds back optimization control instructions to the mobile terminal, and finally the mobile terminal controls the host sampler to execute the operation of the entire sampler's working parameters; therefore, the flow adjustment of the host sampler includes at least three control methods.

[0072] The embodiment of the present invention provides an intelligent air sampler, which can monitor the sampling flow in real time through the flow sensor and Bluetooth module or GPRS communication module in the host sampler to ensure the continuity and stability of the sampling process. At the same time, the APP of the mobile terminal can receive and process data in real time for data analysis, and then timely judge whether the flow is less than the minimum flow threshold or greater than the maximum flow threshold, and detect abnormal flow; when the flow is confirmed to be abnormal, the corresponding control instruction is generated (for example: pump speed control to change the flow), to ensure that the sampling flow is maintained within the optimal range.

[0073] The system architecture of the embodiment of the present invention adopts a three-layer architecture design of a host sampler, a mobile terminal and a remote server. The host sampler is responsible for actual sampling and preliminary data collection, the mobile terminal is responsible for data processing and real-time control, and the remote server is responsible for data storage and in-depth analysis. The host sampler monitors the sampling flow in real time through a built-in flow sensor, and transmits the sampling data and flow data to the mobile terminal through a Bluetooth module or a GPRS communication module. This wireless transmission method improves the flexibility and portability of the system. After receiving the data, the mobile terminal processes it through the data analysis module, and then generates control instructions using the flow control module. The control instructions are sent back to the host sampler via Bluetooth to achieve real-time adjustment of the sampling flow. This closed-loop control process ensures the stability of the sampling flow.

[0074] like Figure 2 As shown, the host sampler 10 also includes: a flow sensor 12, which is used to monitor the sampling flow in real time; a processing unit 13, which is used to process the data of the flow sensor to obtain the sampling data and flow data of the current sampling sample; the sampling data includes the dust composition of the current sampling sample; the flow data is the sampling amount; a storage unit 14, which is used to temporarily store the sampling data and flow data; the processing unit 13 sends the processed data to the mobile terminal via a Bluetooth module or a GPRS communication module.

[0075] like Figure 3 As shown, the APP application 21 of the mobile terminal includes:

[0076] The data receiving module 211 is used to receive the sampling data and flow data sent by the host sampler;

[0077] The data analysis module 212 is used to analyze the received flow data and determine whether the current flow data is less than the minimum flow threshold or greater than the maximum flow threshold;

[0078] The flow control module 213 is used to generate a flow control instruction and obtain first abnormal data information when judging that the current flow data is less than the minimum flow threshold or greater than the maximum flow threshold; the first abnormal data information includes the ID number of the current host sampler and the current host sampler flow;

[0079] The flow control module 214 is used to send the generated flow control instruction to the host sampler through the Bluetooth module or the GPRS communication module.

[0080] It should be noted that the above-mentioned technical implementation method is used to realize the intelligent monitoring function of the APP end. The APP application is mainly used for data reception, analysis and even feedback control. It can realize real-time monitoring and threshold control of traffic to ensure the stability of sampling traffic.

[0081] Preferably, as an implementable solution, the remote server is connected to the mobile terminal via a network; and the mobile terminal uploads the sampling data and flow data to the remote server.

[0082] like Figure 4 As shown, the remote server 30 also includes:

[0083] Database 31, used to store historical sampling data and historical flow data;

[0084] A machine learning model module 32, used for analyzing historical sampling data and historical flow data to obtain a detection model, performing abnormality monitoring on currently acquired sampling data and flow data based on the detection model, and outputting second abnormal data information of the flow data;

[0085] The second abnormal data information includes the ID number of the current host sampler and the current host sampler flow.

[0086] It should be noted that the above-mentioned technical implementation method connects the remote server with the mobile terminal, so that the user can realize remote monitoring and control, adapt to the needs of modern environmental monitoring, and improve work efficiency; at the same time, after data analysis, the second abnormal data information of the flow data is output to realize the alarm sending operation of the ID number of the current host sampler, so as to inform the timely inspection and discovery of the current host sampler.

[0087] Preferably, as an implementable solution, the data structure of the historical sampling data also includes: workplace, timestamp range, sample ID, dust composition; the data structure of the historical flow data includes flow data;

[0088] The machine learning model module 32 specifically includes a first processing module and a second processing module; the first processing module is used to perform regression analysis training on the data structure of the historical sampling data and the data structure of the historical flow data when analyzing the historical sampling data and the historical flow data to obtain the detection model, and obtain a mapping relationship table between the dust composition and the flow data range threshold value in the current workplace in the target timestamp range segment;

[0089] The second processing module is an anomaly detection module; the second processing module is used to judge whether the current flow data significantly deviates from the mean of the historical flow data of the current workplace in the current timestamp range segment based on the real-time data of the dust composition and flow data of the current workplace in the current timestamp range segment; if the deviation value exceeds 15%, it is deemed to be a significant deviation and a second abnormal data information is sent.

[0090] It should be noted that in the design of intelligent air samplers, the relationship between flow data and sampling data is key, because this relationship directly affects the accuracy and effectiveness of sampling. The following is a specific explanation of the relationship, as well as an example.

[0091] The relationship between flow data and sampling data; Flow data: refers to the flow of air or gas passing through the sampler within a specific time, usually expressed in volume units (such as liters / minute). Flow data reflects the rate at which the gas passes through the sampler. Sampling data: refers to the composition and concentration of the sample collected within a specific time, usually including the concentration values ​​of dust, gas components, etc. Sampling data reflects the quality and composition of the sampled medium.

[0092] The relationship between the two: Ideally, there is a certain proportional relationship between flow data and sampling data. For example, when the flow increases, the amount of sample inhaled by the sampler per unit time increases, resulting in an increase in the component concentration value in the sampling data. The flow data must be maintained within a certain threshold range to ensure the accuracy of the sampling data. At low flow, sampling may be incomplete, resulting in low sampling data; at too high flow, excess air may be introduced, reducing the representativeness of the sample; at the same time, based on historical data analysis, it can be found that each workplace is affected by the process or the shift system. The working hours of its production line or other equipment are regular, so the dust concentration generated within its specific timestamp range is also regular. Therefore, it is of great significance to obtain a mapping relationship table between the dust composition of the current workplace in the target timestamp range and the flow data range threshold, which can promptly discover numerical anomalies or even fluctuations within a specific time range.

[0093] Case description: Assume that a smart air sampler is used to monitor the dust concentration in a factory environment. The dust standard of the factory area is 50 micrograms per cubic meter. When the flow rate is maintained at 10 liters / minute, the sampler can accurately collect dust data.

[0094] Normal working state: flow data: 10 liters / minute; sampling data: sample analysis shows that the dust concentration is 45 micrograms / cubic meter; analysis: at this flow rate, the sampler can work stably, and the sampling data reflects the actual concentration of dust in the environment.

[0095] Low flow state: Flow data: 3 liters / minute; Sampling data: Sample analysis shows that the dust concentration is 20 micrograms / cubic meter; Analysis: The flow rate is too low, resulting in insufficient sampling, and the sampling data is low, which fails to truly reflect the dust concentration in the environment.

[0096] High flow state: Flow data: 15 liters / minute; Sampling data: Sample analysis shows that the dust concentration is 70 micrograms / cubic meter; Analysis: The flow rate is too high, which may have introduced tiny particles from the surrounding air, causing the sampling data to be high and lose its representativeness.

[0097] Preferably, as an implementable embodiment, the APP application of the mobile terminal further includes:

[0098] A user interface module for displaying real-time sampling data and flow data;

[0099] An alarm module, configured to issue an alarm when second abnormal data information is detected;

[0100] The remote control module is used to accept the input instructions of the user through the user interface module and perform the operation of remotely adjusting the sampling parameters of the host sampler; the sampling parameters include increasing or decreasing the working speed of the sampling pump.

[0101] The user interface of the mobile terminal can display sampling and flow data in real time, ensuring that users can monitor the status of the equipment at any time. When the system detects an abnormality, the alarm module will promptly remind the user, enhancing the safety and reliability of the system.

[0102] The APP application of the above mobile terminal is also used to realize intelligent feedback; the APP application realizes rapid response to user operation instructions, and the user can directly adjust the working parameters of the sampler through the interface, which enhances the user's operation experience and control flexibility. Through the optimized control instruction feedback of the remote server, the working state of the sampler can be dynamically adjusted to ensure the sampling quality and data accuracy.

[0103] To sum up, an intelligent air sampler provided by an embodiment of the present invention focuses on protecting the system, that is, it is composed of a host sampler equipped with a Bluetooth module or a GPRS communication module or other communication module and an application program of a mobile terminal, and a mobile phone APP application is installed on the mobile terminal used by each operator; the two interact with each other to perform sampling and data caching storage and data sensing and sending of the host sampler, and send them to the mobile phone APP application at the same time, and the mobile phone APP application completes the final data storage and calculation; this can save the computing power of the host sampler and improve the detection level and detection accuracy.

[0104] At the same time, the gas flow rate of the host sampler can be controlled by feedback through the mobile phone APP application, so as to ensure the constant and stable sampling flow rate of the sampler, and ensure the stable and efficient operation of the sampler. At the same time, it uses the mobile phone APP and Bluetooth communication to realize the method of sampler flow monitoring and feedback control, which realizes the implementation monitoring of the user's current sampler flow, and can provide intelligent monitoring and feedback control for the current sampler, so as to ensure the constant and stable sampling flow rate of the sampler, and ensure the stable and efficient operation of the sampler and remote collaborative control.

[0105] The objects of the above sampling are mainly dust (coal dust particles, and other mineral dust particles) and other industrial inhalable particulate matter generated during the production process of production enterprises or production units.

[0106] Embodiment 2

[0107] See also Figure 5 In a second aspect, a second embodiment of the present invention provides a sampler flow monitoring feedback control method, which uses the intelligent air sampler in the first embodiment to perform flow monitoring feedback control operations, including the following steps:

[0108] S10, the host sampler collects samples and monitors the current flow;

[0109] S20, the host sampler sends the sampling data and flow data to the mobile terminal via Bluetooth;

[0110] S30, the mobile terminal receives data, stores data, performs data operations, and sends control instructions to the host sampler; at the same time, the mobile terminal also forwards the received data to the remote server;

[0111] S40, when the mobile terminal determines that the current flow data is less than the minimum flow threshold or greater than the maximum flow threshold, it obtains the first abnormal data information and generates a flow control instruction; the generated flow control instruction is sent to the host sampler through the Bluetooth module or the GPRS communication module;

[0112] S50, the remote server performs a database analysis on the forwarded data to obtain second abnormal data information, and feeds back an optimization control instruction to the mobile terminal according to the second abnormal data information;

[0113] S60. The host sampler adjusts the sampling flow rate according to the received control instruction.

[0114] Embodiment 2 of the present invention provides a sampler flow monitoring feedback control method, which realizes a complete monitoring feedback control process, that is, a multi-level control mechanism is realized by establishing a closed loop of data acquisition-transmission-analysis-control, thereby ensuring the stable operation of the intelligent air sampler and ensuring that its flow anomalies can be discovered in time.

[0115] See also Figure 6 , the step S50 specifically includes the following steps:

[0116] S51, the mobile terminal uploads the sampling data and flow data to the remote server;

[0117] S52, the remote server performs in-depth analysis on the data, detects abnormalities in the sampled data and sampled traffic, and obtains second abnormal data information;

[0118] S53: The remote server then feeds back an optimization control instruction to the mobile terminal according to the second abnormal data information.

[0119] Preferably, as an implementable embodiment, the deep analysis step of the remote server includes:

[0120] Perform regression analysis training on the data structure of historical sampling data and the data structure of historical flow data to obtain a mapping relationship table between dust components in the current workplace within the target timestamp range and flow data range thresholds;

[0121] Based on the real-time data of the dust composition and flow data of the current workplace in the current timestamp range, a judgment is made to determine whether the current flow data significantly deviates from the mean of the historical flow data of the current workplace in the current timestamp range; if the deviation value exceeds 15%, it is deemed to be a significant deviation and a second abnormal data information is sent.

[0122] The remote server uses database analysis and machine learning models to conduct in-depth analysis of historical sampling data and flow data, establish detection models, and monitor abnormal situations in real time. By setting a deviation threshold (such as 15%), when flow data deviates significantly from the historical mean, the system can promptly identify and feedback abnormal information to ensure the normal operation of the equipment.

[0123] Preferably, as an implementable embodiment, the method further comprises the following steps:

[0124] The mobile terminal displays sampling data and flow data in real time;

[0125] When an alarm is issued when the second abnormal data information is detected, the mobile terminal issues an alarm;

[0126] The user receives an operation of remotely adjusting the sampling parameters of the host sampler through the mobile terminal; the sampling parameters include increasing or decreasing the working speed of the sampling pump.

[0127] To sum up, the example of the present invention proposes an intelligent air sampler and a sampler flow monitoring feedback control method. The intelligent air sampler and the flow monitoring feedback control method of the present invention provide an efficient and intelligent environmental monitoring solution, which can monitor and adjust the sampling flow in real time and accurately, ensure the reliability of the sampling data, and have broad application prospects.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. A person skilled in the art may modify the technical solutions described in the above embodiments, or replace part or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent air sampler, characterized in that: Including host sampler, mobile terminal and remote server: The host sampler is provided with a Bluetooth module or a GPRS communication module; The mobile terminal is installed with an APP application; The host sampler is used to collect samples, cache data and send the data to the mobile terminal via a Bluetooth module or a GPRS communication module; The mobile terminal is used to receive data, store data, perform data operations, and send control instructions to the host sampler; the mobile terminal is also used to forward the received data to the remote server; the mobile terminal is used to obtain the first abnormal data information when it is determined that the current flow data is less than the minimum flow threshold or greater than the maximum flow threshold, and generate a flow control instruction; the generated flow control instruction is sent to the host sampler through a Bluetooth module or a GPRS communication module; The remote server performs database analysis on the forwarded data to obtain second abnormal data information, and feeds back an optimization control instruction to the mobile terminal according to the second abnormal data information.

2. The intelligent air sampler according to claim 1, characterized in that: The host sampler also includes: a flow sensor for real-time monitoring of the sampling flow; a processing unit for processing the data of the flow sensor to obtain the sampling data and flow data of the current sampling sample; the sampling data includes the dust composition of the current sampling sample; the flow data is the sampling volume; a storage unit for temporarily storing the sampling data and flow data; the processing unit sends the processed data to the mobile terminal via a Bluetooth module or a GPRS communication module.

3. The intelligent air sampler according to claim 2, characterized in that: The APP application of the mobile terminal includes: A data receiving module, used for receiving sampling data and flow data sent by the host sampler; A data analysis module is used to analyze the received traffic data and determine whether the current traffic data is less than a minimum traffic threshold or greater than a maximum traffic threshold; A flow control module, for generating a flow control instruction and obtaining first abnormal data information when judging that the current flow data is less than a minimum flow threshold or greater than a maximum flow threshold; the first abnormal data information includes an ID number of the current host sampler and the current host sampler flow; The flow control module is used to send the generated flow control instruction to the host sampler through the Bluetooth module or the GPRS communication module.

4. The intelligent air sampler according to claim 3, characterized in that: The remote server is connected to the mobile terminal via a network; the mobile terminal uploads the sampling data and flow data to the remote server.

5. The intelligent air sampler according to claim 4, characterized in that: The remote server also includes: Database, used to store historical sampling data and historical flow data; A machine learning model module, used for analyzing historical sampling data and historical flow data to obtain a detection model, performing abnormality monitoring on currently acquired sampling data and flow data based on the detection model, and outputting second abnormal data information of the flow data; The second abnormal data information includes the ID number of the current host sampler and the current host sampler flow.

6. The intelligent air sampler according to claim 5, characterized in that: The data structure of the historical sampling data also includes: workplace, timestamp range, sample ID, and dust composition; the data structure of the historical flow data includes flow data; The machine learning model module specifically includes a first processing module and a second processing module; the first processing module is used to perform regression analysis training on the data structure of the historical sampling data and the data structure of the historical flow data when analyzing the historical sampling data and the historical flow data to obtain the detection model, and obtain a mapping relationship table between the dust composition and the flow data range threshold value in the current workplace in the target timestamp range segment; The second processing module is an anomaly detection module; the second processing module is used to judge whether the current flow data significantly deviates from the mean of the historical flow data of the current workplace in the current timestamp range segment based on the real-time data of the dust composition and flow data of the current workplace in the current timestamp range segment; if the deviation value exceeds 15%, it is deemed to be a significant deviation and a second abnormal data information is sent.

7. The intelligent air sampler according to claim 6, characterized in that: The APP application of the mobile terminal also includes: A user interface module for displaying real-time sampling data and flow data; An alarm module, configured to issue an alarm when second abnormal data information is detected; The remote control module is used to accept the input instructions of the user through the user interface module and perform the operation of remotely adjusting the sampling parameters of the host sampler; the sampling parameters include increasing or decreasing the working speed of the sampling pump.

8. A sampler flow monitoring feedback control method, characterized in that: The intelligent air sampler according to claims 1 to 7 is used to perform flow monitoring feedback control operations, comprising the following steps: S10, the host sampler collects samples and monitors the current flow; S20, the host sampler sends the sampling data and flow data to the mobile terminal via Bluetooth; S30, the mobile terminal receives data, stores data, performs data operations, and sends control instructions to the host sampler; at the same time, the mobile terminal also forwards the received data to the remote server; S40, when the mobile terminal determines that the current flow data is less than the minimum flow threshold or greater than the maximum flow threshold, it obtains the first abnormal data information and generates a flow control instruction; the generated flow control instruction is sent to the host sampler through the Bluetooth module or the GPRS communication module; S50, the remote server performs a database analysis on the forwarded data to obtain second abnormal data information, and feeds back an optimization control instruction to the mobile terminal according to the second abnormal data information; S60. The host sampler adjusts the sampling flow rate according to the received control instruction.

9. The method according to claim 8, characterized in that Step S50 specifically includes the following steps: S51, the mobile terminal uploads the sampling data and flow data to the remote server; S52, the remote server performs in-depth analysis on the data, detects abnormalities in the sampled data and sampled traffic, and obtains second abnormal data information; S53: The remote server then feeds back an optimization control instruction to the mobile terminal according to the second abnormal data information.

10. The method according to claim 8, characterized in that The in-depth analysis step of the remote server includes: Perform regression analysis training on the data structure of historical sampling data and the data structure of historical flow data to obtain a mapping relationship table between dust components in the current workplace within the target timestamp range and flow data range thresholds; Based on the real-time data of the dust composition and flow data of the current workplace in the current timestamp range, a judgment is made to determine whether the current flow data significantly deviates from the mean of the historical flow data of the current workplace in the current timestamp range; if the deviation value exceeds 15%, it is deemed to be a significant deviation and a second abnormal data information is sent.

11. The method according to claim 10, characterized in that The following steps are also included: The mobile terminal displays sampling data and flow data in real time; when an alarm is issued when the second abnormal data information is detected, the mobile terminal issues an alarm; the user receives an operation of remotely adjusting the sampling parameters of the host sampler through the mobile terminal; the sampling parameters include increasing or decreasing the operating speed of the sampling pump.

Images