Particulate matter monitoring

Patent metadata

Field	Value
Publication number	US-10914716-B2
Application number	US-201916437848-A
Country	US
Kind code	B2
Filing date	Jun 11, 2019
Priority date	Nov 28, 2016
Publication date	Feb 9, 2021
Grant date	Feb 9, 2021

Abstract

Techniques for monitoring particulate matter (PM) mass concentration using relatively low cost devices are described. A computer-implemented method comprises determining, by a device operatively coupled to a processor, relationships between: first PM mass data determined by a monitor station device for a first atmospheric area over a period of time; first PM count data determined by a reference PM count device for the first atmospheric area over the period of time; and first conditional information comprising first values for defined conditional parameters, wherein the first values are associated with the first atmospheric area over the period of time. The method further includes generating an initial conversion model based on the relationships, wherein the conversion model converts a PM count to a PM mass based on one or more conditional parameters of the defined conditional parameters and features for updating the conversion model.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
determining, by one or more components operatively coupled to a processor, relationships between first particulate matter mass data, first particulate matter count data and first conditional information,
wherein the first particulate matter mass data was determined by a monitor station device for a first atmospheric area over a period of time,
wherein the first particulate matter count data was determined by a reference particulate matter count device for the first atmospheric area over the period of time, and
wherein the first conditional information comprises first values for defined conditional parameters, wherein the first values are associated with the first atmospheric area over the period of time;

determining, by the one or more components, a conversion model based on the relationships, wherein the conversion model converts a particulate matter count to a particulate matter mass based on one or more conditional parameters of the defined conditional parameters; and
evaluating, by the one or more components, second particulate matter mass data determined by the monitor station device for the first atmospheric area over a second period of time, wherein the second particulate matter mass data is associated with second particulate matter count data determined by the reference particulate matter count device for the first atmospheric area over the second period of time.

2. The computer-implemented method of claim 1 , further comprising:
receiving, by the one or more components, second conditional information; and
updating, by the one or more components, the conversion model, in response to the receiving the second conditional information.

3. The computer-implemented method of claim 1 , wherein the defined conditional parameters are selected from a group consisting of accumulated pulse height, accumulated pulse area and relative direct current offset.

4. The computer-implemented method of claim 1 , wherein the defined conditional parameters are selected from a group consisting of: particle composition, size distribution, temperature, and humidity.

5. The computer-implemented method of claim 1 , wherein the determining the conversion model comprises employing machine learning.

6. The computer-implemented method of claim 1 , wherein the reference particulate matter count device is located within a defined distance relative to the monitor station device.

7. The computer-implemented method of claim 1 , further comprising:
employing, by the one or more components, the conversion model to determine a current particulate matter mass for the first atmospheric area based on second particulate matter count data determined for the first atmospheric area and second conditional information comprising second values for the one or more conditional parameters, wherein the second values are associated with the first atmospheric area.

8. The computer-implemented method of claim 7 , wherein the second particulate matter count data was determined by a particulate matter count device, and wherein the particulate matter count device is remote from the monitor station device.

9. The computer-implemented method of claim 1 , further comprising:
receiving, by the one or more components, the second particulate matter mass data; and
determining, by the one or more components, second conditional information comprising second values for the defined conditional parameters, wherein the second values are associated with the first atmospheric area over the second period of time, and wherein the second particulate matter mass data is associated with second particulate matter count data determined by the reference particulate matter count device for the first atmospheric area over the second period of time.

10. The computer-implemented method of claim 9 , further comprising:
updating, by the one or more components, the conversion model based on the second particulate matter count data, the second particulate matter mass data, and the second conditional information.

11. The computer-implemented method of claim 1 , wherein the reference particulate matter count device comprises a light scattering device, and wherein the monitor station device is selected from the group consisting of: a tapered element oscillating microbalance device and a beta ray attenuation device.

12. A system, comprising:
a memory that stores computer executable components;
a processor that executes computer executable components stored in the memory, wherein the computer executable components comprise:
a reception component that receives first particulate matter mass data determined by a first device monitor station device for a first atmospheric area over a period of time and first particulate matter count data determined by a first particulate matter count sensor device for the first atmospheric area over a first period of time, wherein the first device monitor station device and the first particulate matter count sensor device are located within a defined distance;
a parameter extraction component that determines first conditional information comprising first values for defined conditional parameters, wherein the first values are associated with the first atmospheric area over the period of time; and
a model generation component that determines one or more conversion models based on the first particulate matter count data, the first particulate matter mass data, and the first conditional information, wherein the one or more conversion models convert a particulate matter count to a particulate matter mass based on one or more conditional parameters of the of the defined conditional parameters, wherein the first particulate matter mass data comprises particulate matter mass concentration levels for the first atmospheric area over the first defined period of time, and wherein the model generation component determines a first conversion model associated with different pollution states based on particulate mass concentration levels.

13. The system of claim 12 , wherein the defined conditional parameters comprise accumulated pulse height and accumulated pulse area.

14. The system of claim 12 , wherein the defined conditional parameters comprise relative direct current offset.

15. The system of claim 14 , wherein the first values comprise relative direct current offset values respectively associated with the particulate matter mass concentration levels, and wherein the model generation component determines a threshold relative direct current offset value associated with a high pollution state based on a subset of the relative direct current offset values respectively associated with a subset of the particulate matter mass concentration levels within a threshold mass concentration level range.

16. The system of claim 12 , further comprising:
a model selection component that selects the first conversion model or the second conversion model to employ in association with determining a current particulate matter mass for the first atmospheric area or a second atmospheric area based on second particulate matter count data for the first atmospheric area or the second atmospheric area and second conditional information for the first atmospheric area or the second atmospheric area,
wherein the second conditional information comprises second values for the defined conditional parameters associated with the first atmospheric area or the second atmospheric area at a current time, including a current relative direct current offset value, and
wherein the model selection component selects the first co

Assignees

• IBM

Inventors

• Wang Junsong
• Wang Lingyun

Classifications

• G01N15/0205

  by optical means · CPC title

• G01N2015/0046

  in gas, e.g. smoke · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G01N33/0027 Primary

  concerning the detector · CPC title