A method and system for online monitoring of dust concentration
By combining light scattering and filter membrane weighing methods, and utilizing historical data and humidity information for classification, the accuracy problem of dust concentration monitoring in high humidity environments was solved, achieving highly accurate and real-time online dust concentration monitoring.
Patent Information
- Application Number
- CN202411230564.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-09-04
AI Technical Summary
Existing dust concentration monitoring methods have low accuracy in high humidity environments. The light scattering method is affected by humidity, leading to measurement errors, while the filter membrane weighing method is cumbersome and cannot be monitored in real time.
By combining light scattering and filter membrane weighing methods, and through historical data analysis and humidity information classification, the corrected dust concentration is obtained, and online monitoring is achieved using an anomaly detection algorithm.
This improves the accuracy and real-time performance of dust concentration monitoring, ensuring the reliability and precision of monitoring results under varying humidity conditions.
Smart Images

Figure CN118730839B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of dust monitoring, and specifically to an online dust concentration monitoring method and system. Background Art
[0002] Dust is a form of air pollution, and long-term exposure to high concentrations of dust may cause serious health problems, including respiratory diseases, lung diseases, and even cancer. In addition to health risks, high concentrations of dust may also increase the risk of industrial accidents, such as explosions and fires. Dust emissions not only affect human health, but may also have serious impacts on the environment, including pollution of soil and water bodies. With the development of sensor technology and data processing technology, online monitoring systems for dust concentration have become more accurate, reliable, and easy to use. These systems can provide data in real time, helping companies to adjust production processes in a timely manner to reduce dust emissions.
[0003] When monitoring dust concentration, it may be affected by various environmental factors, which may lead to unreliable dust concentration. Therefore, it is necessary to correct the dust concentration obtained based on the collection equipment to obtain more realistic dust concentration information. The collection principle of the dust concentration collection equipment used in this application is to obtain dust concentration information using the light scattering method. The light scattering method for monitoring dust concentration makes up for the shortcomings of the membrane weighing method to a certain extent. It is fast, simple, and can perform real-time monitoring. However, its accuracy is affected by the refractive properties, composition, and morphology of dust particles, and relative humidity is considered to be an important influencing factor. According to relevant research, dust particles in the air contain a large amount of hydrophilic components. When the air humidity is high, the hydrophilic components absorb water and condense, which enhances the light scattering ability of the dust particles, thereby causing measurement errors. Summary of the invention
[0004] In order to solve the technical problem of low dust measurement accuracy, this application provides a method and system for online monitoring of dust concentration. The technical solutions adopted are as follows:
[0005] In the first aspect, the present application proposes a method for online monitoring of dust concentration, the method comprising the following steps:
[0006] The dust concentration in different collection areas at the current time and at historical times is collected through light scattering method and filter membrane weighing method, and the humidity value at the current time and at historical times is collected through sensors;
[0007] The dust concentrations collected by the light scattering method and the filter membrane weighing method are recorded as the first concentration and the second concentration respectively; the historical moments with the same humidity are divided into one category, and the measurement deviation of each category is obtained according to the difference between the first concentration and the second concentration of all the collection areas at all the historical moments of each category;
[0008] Calculate the difference of the first concentration between different collection areas at each moment, compose a sequence of all the differences of the first concentration of each collection area, and obtain the spatial similarity between the moments according to the sequence difference of all the same collection areas at different moments; obtain the similarity between the moments according to the spatial similarity, humidity difference and first concentration difference between the moments; record the historical moments with a similarity greater than a preset threshold as reference moments, and use the similarity between the current moment and the reference moment as a weight and the second concentration of each collection area at the reference moment to obtain the reference concentration of each collection area at the current moment;
[0009] Obtain a reference weight based on the difference between the original measurement deviation of the class at the current moment and the measurement deviation of the class after the current moment; obtain a corrected dust concentration by weighting the reference weight with the first concentration of each collection area at the current moment and the reference concentration;
[0010] The corrected dust concentration at the current moment is monitored online through an anomaly detection algorithm.
[0011] In the above scheme, the dust concentration is measured by using a light scattering method device to ensure real-time monitoring. At the same time, the present application analyzes the dust concentration information collected by the collection device of the membrane weighing method and the collection device of the present application based on the history, obtains the dust concentration reference value based on the historical data, and corrects the dust concentration information collected in real time, so that the detection speed is guaranteed while the detection accuracy is guaranteed, which greatly improves the accuracy and real-time performance of the online monitoring of dust concentration. When analyzing based on historical data, the present application not only combines the characteristics of inaccurate detection caused by the influence of humidity information on the light scattering method, but also performs real-time detection and analysis on the humidity information, and classifies the historical data in combination with the humidity information, so that the reference value of the historical reference value obtained is more reliable. When analyzing the historical reference data, not only the difference in the concentration information collected at each position is analyzed, but also the difference in the dust concentration information at different positions is analyzed, so that the dust concentration information obtained not only considers the difference in the concentration value, but also considers the difference in the relative position relationship, so that the results obtained based on the historical data analysis are more reliable and credible.
[0012] In one embodiment, the method for obtaining the measurement deviation of each class according to the difference between the first concentration and the second concentration of all acquisition areas at all historical moments of each class is:
[0013] The difference between the first concentration and the second concentration of each acquisition area at each historical moment is recorded as the concentration difference, and the measurement deviation of each class is obtained according to the concentration difference of all acquisition areas at all historical moments in each class;
[0014] The measurement deviation of each class is proportional to the difference in concentration across all acquisition areas at all times within the class.
[0015] In one embodiment, the method for obtaining the measurement deviation of each class according to the concentration difference of all acquisition areas at all historical moments in each class is:
[0016] The absolute value of the difference between the first concentration and the second concentration of each collection area at each historical moment is recorded as the concentration difference of each collection area at each historical moment;
[0017] Measurement deviation , represents the first concentration of the jth collection area at the uth historical moment, represents the second concentration of the jth collection area at the uth historical moment, S represents the number of historical moments in the class, Indicates the number of collection areas, represents the measurement deviation of the c-th class.
[0018] In one embodiment, the method of calculating the difference of the first concentration between different acquisition areas at each moment, forming a sequence of all the differences of the first concentration of each acquisition area, and obtaining the spatial similarity between the moments according to the sequence differences of all the same acquisition areas at different moments is:
[0019] Any collection area at any time is recorded as the target area, the absolute value of the difference between the first concentration of the target area and the first concentration of the remaining collection areas is calculated, all the collection areas are labeled, and the absolute values of the differences are sorted from small to large according to the labels to obtain a difference sequence;
[0020] The differences between the difference sequences of the same acquisition area at two moments are obtained. The spatial similarity between the two moments is negatively correlated with the differences between the difference sequences of all acquisition areas.
[0021] In one embodiment, the method for obtaining the similarity between the moments according to the spatial similarity, humidity difference and first concentration difference between the moments is:
[0022] The absolute value of the difference between the humidity values at the two moments is recorded as the humidity difference;
[0023] The average of the absolute values of the differences of the first concentrations of all the same acquisition areas at two moments is taken as the first concentration difference at two moments;
[0024] The similarity between two moments is negatively correlated with the humidity difference and the first concentration difference between the two moments, and is positively correlated with the spatial similarity between the two moments.
[0025] In one embodiment, the expression of the similarity between the two moments is: , represents the spatial similarity between the a-th moment and the b-th moment, represents the humidity difference between the ath moment and the bth moment, represents the first concentration difference between the ath moment and the bth moment, represents the linear normalization function, Indicates the similarity between the a-th moment and the b-th moment.
[0026] In one embodiment, the method of weighting the similarity between the current moment and the reference moment and the second concentration of each acquisition area at the reference moment to obtain the reference concentration of each acquisition area at the current moment is:
[0027] Let the similarity between the current moment and each reference moment be recorded as the first similarity, and let the ratio of each first similarity to all first similarities be the weight of the current moment and each reference moment;
[0028] The cumulative sum of the products of the weights and the second concentration at all reference moments in the same acquisition area is taken as the reference concentration in this acquisition area at the current moment.
[0029] In one embodiment, the method for obtaining the reference weight according to the difference between the original measurement deviation of the class at the current moment and the measurement deviation of the class after combining with the current moment is:
[0030] Find a class with the same humidity according to the humidity value at the current moment, add the current moment to the class, calculate the measurement deviation at this moment, and when calculating the measurement deviation, use the first concentration at the current moment as the first concentration and the reference concentration at the current moment as the second concentration;
[0031] The reference weight is obtained according to the difference between the class added at the current moment and the class not added at the current moment.
[0032] In one embodiment, the method of obtaining the corrected dust concentration by taking the reference weight as the weight and weighting the first concentration of each collection area at the current moment and the reference concentration is:
[0033] The expression of dust concentration is: , It represents the corrected dust concentration of the jth collection area at the current time n. represents the reference weight, is the dust concentration of the jth sampling area at the current time n, is the reference concentration of the jth sampling area at the current time n.
[0034] In the second aspect, an embodiment of the present application also provides an online dust concentration monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of any one of the above-mentioned online dust concentration monitoring methods are implemented.
[0035] The beneficial effects of this application are as follows:
[0036] By using a light scattering method device to measure the dust concentration, real-time monitoring is guaranteed. At the same time, the present application analyzes the dust concentration information collected by the collection equipment of the membrane weighing method and the collection equipment of the present application based on the history, obtains the dust concentration reference value based on the historical data, and corrects the dust concentration information collected in real time, so that while ensuring the detection speed, the detection accuracy is also guaranteed, greatly improving the accuracy and real-time performance of online monitoring of dust concentration. When analyzing based on historical data, the present application not only combines the characteristics of inaccurate detection caused by the influence of humidity information on the light scattering method, but also performs real-time detection and analysis on humidity information, and classifies historical data in combination with humidity information, so that the reference value of the historical reference value obtained is more reliable. Further, when analyzing historical reference data, not only the difference in concentration information collected at each location is analyzed, but also the difference in dust concentration information at different locations is analyzed, so that the dust concentration information obtained not only considers the difference in concentration value, but also considers the difference in relative position relationship, so that the results obtained based on historical data analysis are more reliable and credible. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0038] Figure 1 A flow chart of a method for online monitoring of dust concentration provided by an embodiment of the present application;
[0039] Figure 2 Flow chart for obtaining the reference concentration of the acquisition area at the current moment. DETAILED DESCRIPTION
[0040] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the dust concentration online monitoring method and system proposed in the present application, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0041] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
[0042] An embodiment of a method for online monitoring of dust concentration:
[0043] The specific scheme of the online dust concentration monitoring method provided by the present application is described in detail below with reference to the accompanying drawings.
[0044] See also Figure 1 , which shows a flow chart of a dust concentration online monitoring method provided by an embodiment of the present application, the method comprising the following steps:
[0045] Step S001, collecting dust concentrations in different collection areas at current and historical times through light scattering method and filter membrane weighing method, and collecting humidity values at current and historical times through sensors.
[0046] For a space, due to the uneven distribution of dust concentration, the dust concentration obtained by only one collection device cannot accurately reflect the dust concentration of the entire space. Therefore, this application sets up multiple collection devices to be evenly placed in the space. The space used in this embodiment is a rectangular space, and the bottom surface of the rectangular space is evenly divided into eight collection areas, and a collection device is placed in each collection area. The implementer can set it evenly according to the shape and size of the space.
[0047] In the present application, the method for monitoring dust concentration is the light scattering method. The light scattering method does not require complicated sample collection and preprocessing processes. The instrument is directly placed in the test environment. The instrument displays the dust concentration in real time by measuring the intensity of scattered light.
[0048] The light scattering method has the characteristics of rapid monitoring and real-time monitoring. However, under different humidity environments, the dust particles in the air contain a large amount of hydrophilic components. When the air humidity is high, the hydrophilic components absorb water and condense, which enhances the light scattering ability of the dust particles, thereby causing measurement errors. The monitoring accuracy will vary. The filter membrane weighing method has the characteristics of accurate concentration monitoring, but its operation process is cumbersome, requires a long sampling time and drying time, and cannot be monitored in real time.
[0049] Therefore, the present application corrects the dust concentration at the current moment based on the dust concentration accurately collected in the history by the filter membrane weighing method.
[0050] Therefore, it is necessary to obtain the dust concentration obtained through two historical methods. For a historical moment, a dust concentration is obtained by the filter membrane weighing method, a dust concentration is obtained by the light scattering method, and the humidity value at the historical moment is collected by the humidity sensor.
[0051] A large number of historical moments are counted. In this embodiment, 10,000 are taken as an example, and all historical moments are recorded as a historical moment set. Then, the dust concentration in the space and the humidity value in the space are collected in real time by the light scattering method. In this application, the dust concentration is monitored every 5 minutes, so real-time data is collected every 5 minutes.
[0052] At this point, the dust concentration and humidity values of the historical time set and the current time are obtained.
[0053] Step S002, record the dust concentrations collected by the light scattering method and the filter membrane weighing method as the first concentration and the second concentration respectively; classify the historical moments with the same humidity into one category, and obtain the measurement deviation of each category based on the difference between the first concentration and the second concentration of all collection areas at all historical moments of each category.
[0054] Due to the principle of collecting dust concentration according to the light scattering method, different humidity conditions will have different impacts on the obtained dust concentration. Therefore, this application corrects the humidity information at different historical moments to obtain the degree of influence on the dust concentration measurement results under different humidity conditions, and then corrects the dust concentration information based on the humidity information.
[0055] The dust concentration obtained by the light scattering method is recorded as the first concentration, and the dust concentration obtained by the filter membrane weighing method is recorded as the second concentration.
[0056] All historical moments are classified according to humidity values, and the same humidity value is regarded as one class, and the historical moments of the same class are analyzed. The measurement deviation of each class is obtained based on the difference between the first concentration and the second concentration at different moments in the same class.
[0057] Since each historical moment corresponds to multiple collection areas, each collection area has a first concentration and a second concentration. The difference between the first concentration and the second concentration of each collection area at each historical moment is recorded as the concentration difference. The measurement deviation of each class is obtained based on the concentration difference of all collection areas at all historical moments in each class.
[0058] The measurement deviation of each class is proportional to the difference in concentration across all acquisition areas at all times within the class.
[0059] It should be noted that positive correlation means that when one variable increases, the other variable also increases, and the two variables change in the same direction. When one variable changes from large to small or from small to large, the other variable also changes from large to small or from small to large. This application does not impose any special restrictions.
[0060] Preferably, in this embodiment, the absolute value of the difference between the first concentration and the second concentration of each collection area at each historical moment is recorded as the concentration difference of each collection area at each historical moment, and the mean of the concentration differences of all collection areas at all historical moments in the class is taken as the measurement deviation of the class. , represents the first concentration of the jth collection area at the uth historical moment, represents the second concentration of the jth collection area at the uth historical moment, S represents the number of historical moments in the class, Indicates the number of collection areas, represents the measurement deviation of the c-th class.
[0061] Preferably, in another embodiment of the present application, the ratio of the maximum value to the minimum value of the first concentration and the second concentration of each acquisition area at each historical moment is recorded as the concentration difference of each acquisition area at each historical moment, and the sum of the concentration differences of all acquisition areas at all historical moments in the class is taken as the measurement deviation of the class. , is the maximum value function, is the minimum function.
[0062] When the concentration difference between the two measurement methods at the same time is greater under the same humidity conditions, the greater the deviation between the two measurement methods.
[0063] At this point, the measured deviations for each class are obtained.
[0064] Step S003, calculate the difference in the first concentration between different collection areas at each moment, compose a sequence of all the differences in the first concentration of each collection area, obtain the spatial similarity between the moments according to the sequence differences of all the same collection areas at different moments; obtain the similarity between the moments according to the spatial similarity, humidity difference and first concentration difference between the moments; record the historical moments with a similarity greater than a preset threshold as reference moments, and weight the similarity between the current moment and the reference moment with the second concentration of each collection area at the reference moment to obtain the reference concentration of each collection area at the current moment.
[0065] Since the dust concentration collected by the light scattering method at the current moment needs to be corrected through all historical moments, it is necessary to obtain the similarity between different historical moments and the current moment. Therefore, the feature value of each moment is constructed, and the similarity between different moments is determined based on the difference in feature values at different moments. Since the current moment only has the dust concentration obtained by the light scattering method, only the first concentration is analyzed when calculating the similarity.
[0066] First, the first eigenvalue at the moment is the humidity value, which reflects the degree of influence of humidity at different moments. The absolute value of the difference between the humidity values at two moments is calculated and recorded as the humidity difference at the two moments.
[0067] Furthermore, for two moments, only when the dust concentration collection areas at the two moments correspond, the subsequent collection area features are reliable. The spatial similarity of the two moments is obtained based on the difference in dust concentration in the same collection area at different moments, and the difference between the difference sequences of the same collection area at two moments is obtained. The spatial similarity between the two moments is negatively correlated with the difference between the difference sequences of all collection areas.
[0068] Preferably, in this embodiment, any collection area at any moment is recorded as the target area, and the absolute value of the difference between the first concentration of the target area and the first concentration of the remaining collection areas is calculated, wherein all collection areas are labeled, and the absolute values of the differences are sorted in ascending order to obtain a difference sequence; the ratios of all element values with the same label in the difference sequence of the same collection area at the a-th moment and the b-th moment constitute a new sequence recorded as a ratio sequence. The difference sequence of the sequence of the first collection area at the a-th moment is a1, a2, ..., a7; the difference sequence of the sequence of the first collection area at the b-th moment is b1, b2, ..., b7; the ratio sequence of the a-th moment and the b-th moment in the first collection area is a1 / b1, a2 / b2, ..., a7 / b7. The spatial similarity between the a-th moment and the b-th moment is , represents the variance of the ratio sequence of the vth acquisition area, Indicates the number of collection areas, represents an exponential function with a natural constant as base, Represents the spatial similarity between the a-th moment and the b-th moment.
[0069] Preferably, in another embodiment of the present application, any acquisition area at any moment is recorded as the target area, and the absolute value of the difference between the first concentration of the target area and the first concentration of the remaining acquisition areas is calculated, wherein all acquisition areas are labeled, and the absolute values of the differences are sorted in ascending order to obtain a difference sequence; the absolute values of the differences of all element values with the same label in the difference sequence of the same acquisition area at the a-th moment and the b-th moment constitute a new sequence recorded as a difference sequence; the difference sequence between the a-th moment and the b-th moment in the first acquisition area is |a1-b1|, |a2-b2|, ..., |a7-b7|; all element values in the difference sequence are accumulated as the difference sum of the difference sequence. The spatial similarity between the a-th moment and the b-th moment is , represents the difference and difference sequence of the vth acquisition area, Represents a linear normalization function. Other normalization functions, such as maximum and minimum normalization, can also be used.
[0070] Based on the spatial similarity obtained from the same acquisition area at different times, the greater the difference between two times in different acquisition areas, the smaller the spatial similarity between the two times, and the smaller the difference between two times in different acquisition areas, the greater the spatial similarity between the two times.
[0071] Furthermore, the absolute values of the differences of the first concentrations of all the same acquisition areas at two moments are averaged as the first concentration difference at two moments.
[0072] The similarity between the two moments is obtained according to the humidity difference, the first concentration difference and the spatial similarity between the two moments.
[0073] The similarity between two moments is negatively correlated with the humidity difference and the first concentration difference between the two moments, and is positively correlated with the spatial similarity between the two moments.
[0074] It should be noted that negative correlation means that when one variable increases, the other variable decreases accordingly, and the two variables change in opposite directions. When one variable changes from large to small or from small to large, the other variable also changes from small to large or from large to small. This application does not impose any special restrictions.
[0075] Preferably, in this embodiment, the expression of the similarity between two moments is: , represents the spatial similarity between the a-th moment and the b-th moment, represents the humidity difference between the ath moment and the bth moment, represents the first concentration difference between the ath moment and the bth moment, represents the linear normalization function, Indicates the similarity between the a-th moment and the b-th moment.
[0076] Preferably, in another embodiment of the present application, the expression of the similarity between two moments is: , Represents the maximum and minimum normalization function.
[0077] The smaller the humidity difference between two moments, the more similar the two moments are; the smaller the concentration difference between all the same collection areas at two moments, the more similar the two moments are; the smaller the concentration difference between each collection area and the remaining collection areas at two moments, the higher the spatial similarity between the two moments, and the more similar the two moments are.
[0078] The similarity between the current moment and all historical moments is obtained by calculating the similarity between two moments. The historical moments with high similarity are used as references, and a similarity threshold is set. When the similarity between the current moment and the historical moment is greater than the similarity threshold, the historical moment is extracted as a reference. In this embodiment, the similarity threshold is set to 0.8, and the implementer can set it by himself, for example, 0.7, 0.75, 0.75.
[0079] The historical moment greater than the similarity threshold is recorded as the reference moment, and the similarity between the current moment and the reference moment is used as the weight to obtain the reference concentration of the current moment by weighting it with the second concentration of the reference moment.
[0080] Preferably, in this embodiment, the weight is obtained as follows: , Indicates the similarity between the current moment n and the mth reference moment, represents the number of reference moments, represents the weight value of the current moment n and the mth reference moment, and the reference concentration is , represents the second concentration of the jth acquisition area at the mth reference moment, It represents the reference concentration of the jth collection area at the current time n. The flowchart for obtaining the reference concentration of the collection area at the current time is as follows: Figure 2 shown.
[0081] At this point, the reference concentration of each collection area at the current moment is obtained.
[0082] Step S004, obtain a reference weight based on the difference between the original measurement deviation of the class at the current moment and the measurement deviation of the class after combining with the current moment; use the reference weight as the weight and the first concentration of each collection area at the current moment and the reference concentration to obtain a corrected dust concentration.
[0083] According to the dust concentration and reference concentration of each collection area at the current moment, it is divided into different classes according to its humidity value, and the measurement deviation is calculated for the class added at the current moment.
[0084] If the current moment is added to the class with the same humidity value, the measurement deviation of the class after adding the current moment is , is the dust concentration of the jth sampling area at the current time n, is the reference concentration of the jth sampling area at the current time n, It represents the measurement deviation of the c-th class after adding the current moment. The current moment belongs to the c-th class.
[0085] Thus, the measurement deviation of the class added at the current moment is obtained, and the difference between the measurement deviation of the class added at the current moment and the measurement deviation of the class is recorded as the influence coefficient at the current moment, and the reference weight is obtained according to the influence coefficient at the current moment and the measurement deviation of the class.
[0086] Preferably, in this embodiment, the reference weight is , represents the linear normalization function, Represents the reference weight.
[0087] Preferably, in this embodiment, the reference weight is , represents the maximum and minimum normalized function, Represents the reference weight.
[0088] When the difference between the class after adding the current moment and the original class is greater, it means that the original class has changed greatly after the current moment is added, that is, there is a large difference between the current moment and the original class, that is, the reference degree of the reference concentration obtained by the original class is lower.
[0089] Based on this, the dust concentration at the current moment is corrected , Indicates the corrected dust concentration of the jth collection area at the current time n.
[0090] At this point, the corrected dust concentration of each collection area at the current moment is obtained.
[0091] Step S005: The corrected dust concentration at the current moment is monitored online through an abnormality detection algorithm.
[0092] The above method is used to correct the obtained dust concentration in real time, and the first concentration of the same collection area at all reference moments is composed into a sequence and recorded as a historical concentration sequence, which is processed by the LOF anomaly detection algorithm. The input is the dust concentration of different collection areas at the current moment and the historical concentration sequence of different collection areas. The output is the LOF value of each collection area, and the anomaly factor threshold is set. When the LOF value is greater than the anomaly factor threshold, the collection area corresponding to the collection area is alarmed. In this embodiment, the anomaly factor is set to 1, and the implementer can also take other values, such as 1.1, 1.2. In this way, the online monitoring of dust concentration is completed.
[0093] Based on the same inventive concept as the above method, an embodiment of the present invention also provides an online dust concentration monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned methods for online dust concentration monitoring when executing the computer program.
[0094] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
[0095] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
Claims
1. A method for online monitoring of dust concentration, characterized in that: The method comprises the following steps: The dust concentration in different collection areas at the current time and at historical times is collected by light scattering method and filter membrane weighing method, and the humidity value at the current time and at historical times is collected by sensors; The dust concentrations collected by the light scattering method and the filter membrane weighing method are recorded as the first concentration and the second concentration respectively; the historical moments with the same humidity are divided into one category, and the measurement deviation of each category is obtained according to the difference between the first concentration and the second concentration of all the collection areas at all the historical moments of each category; Calculate the difference of the first concentration between different collection areas at each moment, compose a sequence of all the differences of the first concentration of each collection area, and obtain the spatial similarity between the moments according to the sequence difference of all the same collection areas at different moments; obtain the similarity between the moments according to the spatial similarity, humidity difference and first concentration difference between the moments; record the historical moments with a similarity greater than a preset threshold as reference moments, and use the similarity between the current moment and the reference moment as a weight and the second concentration of each collection area at the reference moment to obtain the reference concentration of each collection area at the current moment; Obtain a reference weight based on the difference between the original measurement deviation of the class at the current moment and the measurement deviation of the class after the current moment; obtain a corrected dust concentration by weighting the reference weight with the first concentration of each collection area at the current moment and the reference concentration; The corrected dust concentration at the current moment is monitored online through anomaly detection algorithms; The method of calculating the difference of the first concentration between different acquisition areas at each moment, forming a sequence of all the differences of the first concentration of each acquisition area, and obtaining the spatial similarity between the moments according to the sequence differences of all the same acquisition areas at different moments is: Any collection area at any time is recorded as the target area, the absolute value of the difference between the first concentration of the target area and the first concentration of the remaining collection areas is calculated, all the collection areas are labeled, and the absolute values of the differences are sorted from small to large according to the labels to obtain a difference sequence; Obtain the difference between the difference sequences of the same acquisition area at two moments. The spatial similarity between the two moments is negatively correlated with the difference between the difference sequences of all acquisition areas. The method for obtaining the similarity between moments according to the spatial similarity, humidity difference and first concentration difference between moments is: The absolute value of the difference between the humidity values at the two moments is recorded as the humidity difference; The average of the absolute values of the differences of the first concentrations of all the same acquisition areas at two moments is taken as the first concentration difference at two moments; The similarity between two moments is negatively correlated with the humidity difference and the first concentration difference between the two moments, and positively correlated with the spatial similarity between the two moments; The expression of the similarity between the two moments is , represents the spatial similarity between the a-th moment and the b-th moment, represents the humidity difference between the ath moment and the bth moment, represents the first concentration difference between the ath moment and the bth moment, represents the linear normalization function, Indicates the similarity between the a-th moment and the b-th moment.
2. The method for online monitoring of dust concentration according to claim 1, characterized in that: The method for obtaining the measurement deviation of each class according to the difference between the first concentration and the second concentration of all acquisition areas at all historical moments of each class is: The difference between the first concentration and the second concentration of each acquisition area at each historical moment is recorded as the concentration difference, and the measurement deviation of each class is obtained according to the concentration difference of all acquisition areas at all historical moments in each class; The measurement deviation of each class is proportional to the difference in concentration across all acquisition areas at all times within the class.
3. A dust concentration online monitoring method as claimed in claim 2, characterized in that: The method for obtaining the measurement deviation of each class according to the concentration difference of all acquisition areas at all historical moments in each class is: The absolute value of the difference between the first concentration and the second concentration of each collection area at each historical moment is recorded as the concentration difference of each collection area at each historical moment; Measurement deviation , represents the first concentration of the jth collection area at the uth historical moment, represents the second concentration of the jth collection area at the uth historical moment, S represents the number of historical moments in the class, Indicates the number of collection areas, represents the measurement deviation of the c-th class.
4. The method for online monitoring of dust concentration according to claim 1, characterized in that: The method of weighting the similarity between the current moment and the reference moment and weighting the second concentration of each collection area at the reference moment to obtain the reference concentration of each collection area at the current moment is: Let the similarity between the current moment and each reference moment be recorded as the first similarity, and let the ratio of each first similarity to all first similarities be the weight of the current moment and each reference moment; The cumulative sum of the products of the weights and the second concentration at all reference moments in the same acquisition area is taken as the reference concentration in this acquisition area at the current moment.
5. The method for online monitoring of dust concentration according to claim 1, characterized in that: The method for obtaining the reference weight according to the difference between the original measurement deviation of the class at the current moment and the measurement deviation of the class after the current moment is: Find a class with the same humidity according to the humidity value at the current moment, add the current moment to the class, calculate the measurement deviation at this moment, and when calculating the measurement deviation, use the first concentration at the current moment as the first concentration and the reference concentration at the current moment as the second concentration; The reference weight is obtained according to the difference between the class added at the current moment and the class not added at the current moment.
6. The method for online monitoring of dust concentration according to claim 1, characterized in that: The method of obtaining the corrected dust concentration by taking the reference weight as the weight and weighting the first concentration of each collection area at the current moment and the reference concentration is: The expression of dust concentration is: , It represents the corrected dust concentration of the jth collection area at the current time n. represents the reference weight, is the dust concentration of the jth sampling area at the current time n, is the reference concentration of the jth sampling area at the current time n.
7. A dust concentration online monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method for online monitoring of dust concentration as described in any one of claims 1 to 6 are implemented.
