Method and device for evaluating stability of combustion process

Abstract

The invention discloses a combustion process stability evaluation method and device, and relates to the technical field of combustion safety monitoring. Flame static characteristics and flame dynamic characteristics at each moment are extracted; taking the flame static characteristics, the flame dynamic characteristics, the state data and the flue gas emission monitoring data as characteristics, and for any characteristic, calculating a Z score, a linear instability index and a threshold instability index of the corresponding characteristic at each moment; determining a comprehensive instability index of each feature at each moment according to the Z score, the linear instability index and the threshold instability index of each feature at each moment; clustering the data at all moments according to the comprehensive instability index of each feature at each moment to obtain a stability clustering center; and determining a stability evaluation result of the combustion process of the incinerator at each moment according to the distance between the data at each moment and the stability clustering center. The method can accurately evaluate the stability of the combustion process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of combustion safety monitoring, and particularly relates to a stability evaluation method and device for a combustion process. BACKGROUND

[0002] Incinerators are widely used for the treatment of sludge, garbage and industrial waste, and their stable operation is crucial for pollutant emission control and energy utilization efficiency. Existing incinerator control systems mainly rely on Distributed Control System (DCS) for parameter adjustment, and Continuous Emission Monitoring System (CEMS) for monitoring of emission indicators. Although such systems can collect data such as temperature, oxygen content, and fuel flow in real time, they lack in-depth analysis of the combustion state and cannot effectively identify unstable factors in the combustion process.

[0003] Currently, some research attempts to analyze the combustion state using flame images, but most of them are based on static flame features (such as brightness and area) for judgment, ignoring the influence of dynamic changes in the flame on the stability of the combustion process.

[0004] Therefore, there is a lack of a method that can accurately evaluate the stability of the combustion process in the prior art. SUMMARY

[0005] Therefore, it is necessary to provide a stability evaluation method and device for a combustion process, which can accurately evaluate the stability of the combustion process.

[0006] The present application adopts the following technical solutions: The present application provides a stability evaluation method for a combustion process, comprising: acquiring data collected at a plurality of continuous time points, the data at each time point comprising a flame image of the incinerator in the combustion process, and state data and flue gas emission monitoring data; extracting flame static features and flame dynamic features at each time point according to the flame image collected at each time point, respectively; taking the flame static features and the flame dynamic features, and the state data and the flue gas emission monitoring data as features, calculating the Z-score, the linear instability index and the threshold instability index of the corresponding features at each time point for any kind of feature; determining the comprehensive instability index of each feature at each time point according to the Z-score, the linear instability index and the threshold instability index of each feature at each time point; clustering the data at all time points according to the comprehensive instability index of each feature at each time point, to obtain a stability clustering center; According to the distance between the data of each moment and the stability clustering center, the stability evaluation result of the combustion process of the incinerator at each moment is determined.

[0007] Optionally, the flame static features include average brightness and brightness standard deviation; the flame dynamic features include average pulsation frequency, pulsation area rate, average speed and average direction; the flame static features and the flame dynamic features of each moment are extracted according to the flame image collected at each moment, including: The average brightness and the brightness standard deviation of the flame image are calculated for the flame image collected at any moment; The average pulsation frequency of the flame image is calculated according to the flame image and the preset frame flame image collected before the flame image; The pulsation area rate of the flame image is calculated according to the current flame image and the flame images of the adjacent two frames before and after the current flame image; The speed of each pixel point in the flame image is calculated according to the optical flow method, and the average value of the speeds of all pixel points in the flame image is taken as the average speed of the flame image; The speed direction of each pixel point in the flame image is calculated, and the average value of the speed directions of all pixel points in the flame image is taken as the average direction of the flame image.

[0008] Optionally, the linear instability index of each moment corresponding to the feature is calculated, including: For any feature, the feature sequence of the current moment is obtained in a sliding window manner; The feature sequence is linearly fitted by linear regression to determine the slope of linear fitting and the goodness of fit; The absolute value of the product of the slope of linear fitting and the goodness of fit is determined as the linear instability index of the feature.

[0009] Optionally, the threshold instability index of each moment corresponding to the feature is calculated, including: For any feature, when the value corresponding to the feature is greater than or equal to the lower limit of the threshold value and less than or equal to the upper limit of the threshold value, the threshold instability index of the feature is determined as 0; When the value corresponding to the feature is greater than the upper limit of the feature threshold value or less than the lower limit of the feature threshold value, the threshold instability index of the feature is determined according to the value of the feature, the upper limit of the feature threshold value and the lower limit of the feature threshold value.

[0010] Optionally, when the value corresponding to the feature is greater than the upper limit of the feature threshold value, the calculation formula of the threshold instability index of the feature is: ; Wherein, represents the threshold instability index, represents the value of the feature, represents the upper threshold of the feature, Indicates the lower limit of the feature threshold; When the value corresponding to the feature is less than the lower limit of the feature threshold, the calculation formula of the threshold instability index of the feature is: .

[0011] Optionally, a comprehensive instability index of each feature at each moment is determined based on the Z score, linear instability index, and threshold instability index of each feature at each moment, including: For any feature at each moment, the sum of the feature's Z score, linear instability index, and threshold instability index is used to determine the comprehensive instability index of the feature.

[0012] Optionally, data at all times are clustered according to the comprehensive instability index of each feature at each time to obtain stability cluster centers, including: According to the comprehensive instability index of each feature at each moment, the data at all moments are clustered using a variety of different clustering algorithms to obtain the clustering results of each clustering algorithm; the clustering results include stable data clusters and unstable data clusters in the two-dimensional plane; Determine the best clustering algorithm based on the clustering results of each clustering algorithm; The cluster center of the stability data cluster of the best clustering algorithm is determined as the stability cluster center.

[0013] Optionally, the stability evaluation result of the combustion process of the incinerator at each moment is determined based on the distance between the data at each moment and the stability cluster center, including: Determine the incineration system stability index at each moment based on the distance between the data at each moment and the stability cluster center and the preset distance factor; At any moment, if the incineration system stability index is within a first preset range, the stability assessment result is determined to be that the combustion process of the incinerator is stable; If the incineration system stability index is within the second preset range, the stability assessment result is determined to be that the combustion process of the incinerator is relatively stable; If the incineration system stability index is within the third preset range, the stability assessment result is determined to be that the combustion process of the incinerator is unstable; all values ​​within the first preset range are greater than all values ​​within the second preset range, and all values ​​within the second preset range are greater than all values ​​within the third preset range.

[0014] Optionally, the calculation formula of the incineration system stability index is: ; in, represents a stability index of the incineration system, represents a distance between data points and a stability cluster center, represents a distance factor.

[0015] The present application provides a stability evaluation device of a combustion process, comprising: An acquisition module is configured to acquire data collected at a plurality of continuous time points, wherein the data at each time point comprises a flame image of an incinerator in a combustion process, and state data and flue gas emission monitoring data; An extraction module is configured to extract flame static features and flame dynamic features of each time point respectively according to the flame image collected at each time point; A calculation module is configured to take the flame static features and the flame dynamic features, and the state data and the flue gas emission monitoring data as features, and calculate Z scores, linear instability indexes and threshold instability indexes of the corresponding features at each time point for each kind of feature; A comprehensive module is configured to determine comprehensive instability indexes of each kind of feature at each time point according to the Z scores, the linear instability indexes and the threshold instability indexes of each kind of feature at each time point; A clustering module is configured to cluster the data at all time points according to the comprehensive instability indexes of each kind of feature at each time point, to obtain stability cluster centers; A determination module is configured to determine stability evaluation results of the combustion process of the incinerator at each time point according to distances between the data at each time point and the stability cluster centers.

[0016] The present application provides a computer readable storage medium, wherein the storage medium stores a computer program, and the computer program is executed by a processor to implement the above-mentioned stability evaluation method of a combustion process.

[0017] The present application provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the above-mentioned stability evaluation method of a combustion process when executing the program.

[0018] The above-mentioned at least one technical scheme adopted by the present application can achieve the following beneficial effects: In the present application, the state data, the flue gas emission monitoring data and the flame image extracted flame static features and flame dynamic features are taken as features, and then the instability indexes of each feature are calculated, including Z-score, linear instability index and threshold instability index, which are equivalent to defining mutation instability, trend instability and threshold instability, and then based on the three indexes, the comprehensive instability index of the corresponding feature is obtained, the clustering analysis of the comprehensive stability index of each feature calculated is carried out, and the stability clustering center is accurately found out, and on this basis, the stability evaluation result of the combustion process of the incinerator is determined based on the distance from the data to the stability clustering center, so that the accuracy of the combustion process stability evaluation is improved. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the present application. In the drawings: Figure 1 A combustion process stability evaluation method flowchart provided by the present application; Figure 2 The clustering results of four clustering algorithms provided by the present application in a two-dimensional plane, wherein (a) is a clustering result schematic diagram of KMeans clustering in a two-dimensional plane, (b) is a clustering result schematic diagram of hierarchical clustering in a two-dimensional plane, (c) is a clustering result schematic diagram of Gaussian mixture model in a two-dimensional plane, and (d) is a clustering result schematic diagram of DBSCAN model in a two-dimensional plane; Figure 3 A computer device schematic diagram for implementing the combustion process stability evaluation method provided by the present application. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described below in conjunction with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0021] The existing method mainly uses fixed threshold or empirical rule to judge combustion anomaly, lacks unified stability quantitative standard, and is difficult to adapt to complex working condition changes.

[0022] Therefore, there is an urgent need for a combustion process stability evaluation method based on the stability evaluation method, which combines DCS (state data), CEMS (flue gas emission monitoring data) and flame image data, fully considers the dynamic change characteristics of the combustion state, realizes the accurate quantification and real-time monitoring of the stability of the incineration system, and improves the operation stability and emission control level of the incinerator.

[0023] The execution subject of the combustion process stability evaluation method provided in the application can be a server arranged in a business platform, or a device such as a desktop computer, a notebook computer and the like capable of executing the scheme of the application. The technical scheme provided by each embodiment of the application will be described in detail below with reference to the drawings.

[0024] Figure 1 The combustion process stability evaluation method provided in the application is a flowchart, and specifically includes the following steps: S101, acquiring data collected at a plurality of continuous time points, wherein the data at each time point includes flame images in the combustion process of the incinerator, and state data and flue gas emission monitoring data.

[0025] Among them, in the incinerator field, the industrial camera is fixed on the top of the incinerator, a certain number of flame images are continuously shot by the industrial camera, the images are clear and visible, and the data acquisition interval can be 1 minute; specifically, the number of collected images can be determined according to actual needs.

[0026] The state data is DCS data, and the flue gas emission monitoring data is CEMS data, wherein the state data includes fuel feed quantity, primary air quantity, secondary air quantity, auxiliary fuel flow, denitration agent flow, desulfurization agent flow, in-furnace oxygen content, dilute phase zone temperature and dense phase zone temperature, and the flue gas emission monitoring data includes flue gas temperature, NOx emission concentration, SO2 emission concentration, CO emission concentration and HCl emission concentration.

[0027] During the combustion process of the incinerator, the DCS and the CEMS will acquire the state data and the flue gas emission monitoring data in real time, so that after the flame images are collected, the state data and the flue gas emission monitoring data at the corresponding time can be acquired from the database.

[0028] S102, according to the flame images collected at each time point, the flame static features and the flame dynamic features at each time point are extracted respectively.

[0029] Optionally, the static features of the flame include average brightness and brightness standard deviation; the dynamic features of the flame include average pulsation frequency, pulsation area ratio, average speed and average direction; based on the flame image collected at each moment, the static features and dynamic features of the flame at each moment are extracted respectively, including: for the flame image collected at any moment, calculating the average brightness and brightness standard deviation of the flame image; calculating the average pulsation frequency of the flame image based on the flame image and the preset frame flame image collected before the flame image; calculating the pulsation area ratio of the flame image based on the current flame image and the flame images of the two adjacent frames before and after; calculating the speed of each pixel point in the flame image according to the optical flow method, and taking the average speed of all pixel points in the flame image as the average speed of the flame image; calculating the speed direction of each pixel point in the flame image, and taking the average speed direction of all pixel points in the flame image as the average direction of the flame image.

[0030] First, before collecting the static and dynamic features of the flame image, the flame image is Gaussian filtered with a filter kernel size of 5. The filtered flame image is converted into an HSV image, which corresponds to hue, saturation, and value.

[0031] The flame features are extracted based on the V channel of the HSV image. The flame features include flame static features and flame dynamic features. That is, the flame static features and flame dynamic features of the extracted flame image are both extracted based on the V channel of the HSV image corresponding to the flame image.

[0032] (1) Average brightness Extract from HSV image V Channel components, calculate the average brightness, the calculation formula is as follows: (1); in, is the average brightness, is the first The brightness of the pixel, is the number of pixels in the flame area of ​​the flame image.

[0033] (2) Brightness standard deviation The brightness standard deviation can measure the degree of brightness dispersion and reflect the non-uniformity of flame temperature to a certain extent. The brightness standard deviation calculation formula is as follows: (2); in, is the brightness standard deviation.

[0034] (3) Average pulsation frequency The average brightness sequence is calculated by extracting all images within 5 seconds before the current time. The average brightness sequence is processed by discrete Fourier transform and the direct current component is removed. The power spectrum average pulsation frequency is analyzed and processed, and the calculation formula is as follows: (3); In the formula, is the average pulsation frequency; N represents the total number of frequency components in the discrete Fourier transform; is the first frequency component in the discrete Fourier transform, with the unit of Hz; is the first frequency component in the discrete Fourier transform, with the unit of Hz; is the square of the amplitude component of the frequency domain curve.

[0035] (4) Pulsation area rate The pulsation area rate is calculated based on the three-frame difference method to reduce noise interference. Specifically, the V channel data of the adjacent three images (i.e. the current flame image and the previous and next two flame images) are extracted, the first two frames and the last two frames are respectively differentiated, the two differentiation results are logically ANDed, and the V value pulsation data is finally obtained, which reflects the change of the brightness of the pixel points. The pixels with a pulsation size exceeding 3 are defined as significant pulsation pixels, and the ratio of the number of the significant pulsation pixels to the number of pixels in the flame area is the pulsation area rate. The calculation formula is as follows: (4); (5); In the formula, is the V channel data of the first frame, is the V channel data of the first frame, is the V channel data of the first frame, is the V channel data of the first frame, is the V value pulsation data, is the V value pulsation data, is the V value pulsation data, is the step function, is the pulsation threshold, is the number of pixels in the flame area, is the pulsation area rate, represents the number of horizontal pixel of the image, represents the number of vertical pixel of the image, represents the pixel coordinates, is the calculated , is the intersection operation, which represents the logical AND.

[0036] (5) Average speed The average speed is calculated based on the Lucas-Kanada optical flow method. The gradient equation can be obtained by the L-K optical flow method: (6); where, and represent and the velocity in the direction, , and represent the partial derivatives of the luminance in , and .

[0037] Taking a window of 10x10, each point in the window is considered to have the same direction of movement. Applying all the points to the gradient equation gives: (7).

[0038] Solving equation (7) based on the least squares method gives , and the velocity calculation formula is: (8).

[0039] The average velocity of all pixel points in the flame region is calculated, and the average direction is calculated based on the equal interval sampling method.

[0040] (6) Average direction The velocity direction calculation formula of a single pixel point is as follows: (9).

[0041] The average direction of all pixel points in the flame region is calculated.

[0042] S103, the flame static features and the flame dynamic features, and the state data and the flue gas emission monitoring data are all taken as features, and for any kind of feature, the Z-score, the linear instability index and the threshold instability index of the corresponding feature at each time are calculated.

[0043] Instability index extraction: the feature data set includes the aforementioned flame static features and flame dynamic features, and the state data and the flue gas emission monitoring data, and the stability is defined as the change of the parameter relative to the historical data. The parameter stability indicates that the parameter fluctuates in a small range over time. Unstable conditions include: 1, the parameter sharply increases or decreases, obviously deviating from the historical data range; 2, the parameter continuously increases or decreases, having a clear linear trend; 3, the parameter exceeds the specified threshold, exceeding the upper threshold or lower threshold based on experience. Three instability indexes are defined for the three cases: Z-score, linear instability index and threshold instability index.

[0044] Z-score: measure the distance of a data point from the mean of the data set in units of standard deviation, the formula is: (10); Wherein, according to the sliding window mode, the feature set of the current time feature is obtained, for example, the sliding window is 1 hour 60 data points of features, and the feature set includes the features of the previous 1 hour from the current time; At this time, Z-score of the current time feature, is the value of the current time feature, is the mean of the feature set, is the standard deviation of the feature set.

[0045] In one embodiment, the linear instability index of the corresponding feature at each time is calculated, including: for any kind of feature, according to the sliding window mode, the feature sequence of the current time is obtained; the linear fitting of the feature sequence is determined by linear regression, and the slope and fitting degree of linear fitting are determined; the absolute value of the product of the slope and the fitting degree of linear fitting is determined as the linear instability index of the feature.

[0046] The way of obtaining the feature sequence of the current time in this embodiment is the same as the way of obtaining the feature set in the above embodiment, which will not be described here.

[0047] Linear instability index The formula is: (11); In the formula, is the slope of linear fitting, is the fitting degree of linear fitting.

[0048] In one embodiment, the threshold instability index of the corresponding feature at each time is calculated, including: for any kind of feature, in the case that the value corresponding to the feature is greater than or equal to the lower limit of the threshold value and less than or equal to the upper limit of the threshold value, the threshold instability index of the feature is determined as 0; in the case that the value corresponding to the feature is greater than the upper limit of the feature threshold value or less than the lower limit of the feature threshold value, the threshold instability index of the feature is determined according to the value of the feature, the upper limit of the feature threshold value and the lower limit of the feature threshold value. Optionally, in the case that the value corresponding to the feature is greater than the upper limit of the feature threshold value, the formula for calculating the threshold instability index of the feature is: (12); Wherein, denotes the threshold instability index, denotes the value of the feature, denotes the upper limit of the feature threshold value, denotes the lower limit of the feature threshold value.

[0049] In the case where the value of the feature correspondence is less than the lower limit of the feature threshold value, the calculation formula of the threshold instability index of the feature is: (13).

[0050] S104, according to the Z-score, the linear instability index and the threshold instability index of each feature at each time, determine the comprehensive instability index of each feature at each time.

[0051] Optionally, according to the Z-score, the linear instability index and the threshold instability index of each feature at each time, determining the comprehensive instability index of each feature at each time comprises: for any feature at each time, adding the Z-score, the linear instability index and the threshold instability index of the feature to determine the result as the comprehensive instability index of the feature.

[0052] The comprehensive instability index of the feature measures the instability degree of the current data relative to the historical data.

[0053] S105, according to the comprehensive instability index of each feature at each time, clustering the data of all times to obtain a stability clustering center.

[0054] Optionally, according to the comprehensive instability index of each feature at each time, clustering the data of all times to obtain a stability clustering center comprises: according to the comprehensive instability index of each feature at each time, clustering the data of all times by a plurality of different clustering algorithms to obtain the clustering results of each clustering algorithm; the clustering results include stable data clusters and unstable data clusters in a two-dimensional plane; determining the best clustering algorithm according to the clustering results of each clustering algorithm; determining the clustering center of the stable data cluster of the best clustering algorithm as the stability clustering center.

[0055] Specifically, K-means (KMeans) clustering, hierarchical clustering, Gaussian mixture model and density-based spatial clustering of applications with noise (DBSCAN) model can be used for clustering analysis to obtain stable and unstable data clusters, and then principal component analysis (PCA) is used for dimension reduction to reduce the comprehensive instability index of each feature at each time to two dimensions, for example, if there are N features at a time, the N-dimensional comprehensive instability index is reduced to two dimensions; the clustering results of each clustering algorithm are displayed on a two-dimensional plane, and the clustering effects are compared based on the distribution of stable and unstable data clusters to determine the best clustering algorithm.

[0056] Specifically, the best clustering algorithm is determined based on the distribution of the stability and instability data clusters and the clustering effect, including: based on the stability and instability data clusters of each clustering algorithm respectively, the silhouette coefficient of the entire data set corresponding to each clustering algorithm is calculated, and the clustering algorithm corresponding to the maximum silhouette coefficient is determined as the best clustering algorithm.

[0057] As shown in Figure 2 , Figure 2 are four clustering results of the four clustering algorithms in a two-dimensional plane, wherein (a) is a clustering result of KMeans clustering in a two-dimensional plane, (b) is a clustering result of hierarchical clustering in a two-dimensional plane, (c) is a clustering result of Gaussian mixture model in a two-dimensional plane, and (d) is a clustering result of DBSCAN model in a two-dimensional plane.

[0058] S106, according to the distance between the data at each time and the stability clustering center, the stability evaluation result of the combustion process of the incinerator at each time is determined.

[0059] Optionally, according to the distance between the data at each time and the stability clustering center, the stability evaluation result of the combustion process of the incinerator at each time is determined, including: determining the incineration system stability index at each time according to the distance between the data at each time and the stability clustering center and the preset distance factor; for any time, if the incineration system stability index is within a first preset range, it is determined that the stability evaluation result is that the combustion process of the incinerator is stable; if the incineration system stability index is within a second preset range, it is determined that the stability evaluation result is that the combustion process of the incinerator is relatively stable; if the incineration system stability index is within a third preset range, it is determined that the stability evaluation result is that the combustion process of the incinerator is unstable; all values within the first preset range are greater than all values within the second preset range, and all values within the second preset range are greater than all values within the third preset range.

[0060] Optionally, the incineration system stability index is defined based on the Sigmoid function, and the calculation formula of the incineration system stability index is: (14); Among them, represents the incineration system stability index, represents the distance between the data point and the stability clustering center, represents the distance factor. For any time, the data point here is a two-dimensional coordinate point after reducing the dimension of the comprehensive instability index of each feature at the corresponding time after clustering, and the stability clustering center is also a two-dimensional coordinate point at this time.

[0061] The first preset range can be , the second preset range can be , the third preset range can be .

[0062] The incineration system stability index is between , the combustion is stable, and the parameters normally fluctuate; the incineration system stability index is between , the combustion is relatively stable, and the parameters fluctuate in a small range; and the incineration system stability index is between , the combustion is unstable, and some parameters may sharply fluctuate or exceed the normal working condition range.

[0063] The incineration system stability index constructed by the present application can evaluate the overall stability of the incineration process in real time, and provide guidance for combustion optimization and pollutant control. When the index abnormally decreases, it can serve as a warning signal to indicate that the incineration system may have problems such as abnormal pollutant emission or deviation of the temperature in the furnace. At the same time, the present application further provides instability indexes of each characteristic parameter, which helps to identify the source of the abnormality, and these parameters can be optimized and adjusted in combination with process requirements and historical data. For example, when the incineration system stability index is abnormal, if the instability index of the concentration of NOx or CO is large, the combustion temperature or denitration strategy can be optimized.

[0064] When the stability evaluation method of the combustion process provided by the present application is applied, the order of each step shown in Figure 1 may not be executed, and the execution order of each step can be determined as needed, and the present application does not limit this.

[0065] The above is the stability evaluation method of the combustion process provided by one or more embodiments of the present application, based on the same idea, the present application also provides a corresponding stability evaluation device of the combustion process, which comprises: An acquisition module is configured to acquire data collected at a plurality of continuous time points, and each time point data comprises a flame image of the incinerator in the combustion process, state data and flue gas emission monitoring data.

[0066] An extraction module is configured to extract flame static features and flame dynamic features of each time point respectively according to the flame image collected at each time point.

[0067] A calculation module is configured to take the flame static features and the flame dynamic features, and the state data and the flue gas emission monitoring data as features, and calculate the Z-score, the linear instability index and the threshold instability index of the corresponding features at each time point for each kind of feature.

[0068] A comprehensive module is configured to determine the comprehensive instability index of each kind of feature at each time point according to the Z-score, the linear instability index and the threshold instability index of each kind of feature at each time point.

[0069] a clustering module configured to cluster the data of all time points according to the comprehensive instability index of each feature at each time point to obtain stability clustering centers.

[0070] a determining module configured to determine the stability evaluation result of the combustion process of the incinerator at each time point according to the distance between the data of each time point and the stability clustering center.

[0071] The specific limitations of the stability evaluation device for the combustion process can be seen from the limitations of the stability evaluation method for the combustion process in the foregoing, which will not be described here. Each module in the stability evaluation device for the combustion process can be realized by software, hardware and a combination thereof in whole or in part. Each module described above can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0072] The application further provides a computer readable storage medium, which stores a computer program, and the computer program can be used to execute the stability evaluation method for the combustion process. Figure 1 The stability evaluation method for the combustion process is provided.

[0073] The application further provides a computer device. Figure 3 The structure diagram of the computer device is shown in the accompanying drawings. Figure 3 As shown in the accompanying drawings, at the hardware level, the computer device comprises a processor, an internal bus, a network interface, a memory and a nonvolatile memory, and of course can further comprise other hardware required by business. The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs to realize the stability evaluation method for the combustion process. Figure 1 The stability evaluation method for the combustion process is provided.

[0074] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments of the methods. In the embodiments of the present application, any reference to memory, storage, database or other medium can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0075] The technical features of the above embodiments can be combined in any way. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

Claims

1. A method for evaluating the stability of a combustion process, characterized in that: include: Acquire data collected at multiple consecutive moments, where the data at each moment includes flame images of the incinerator during combustion, as well as status data and flue gas emission monitoring data; According to the flame images collected at each moment, the static characteristics and dynamic characteristics of the flame at each moment are extracted respectively; The static and dynamic characteristics of flames, as well as state data and flue gas emission monitoring data, are all used as features. For any feature, the Z score, linear instability index, and threshold instability index of the corresponding feature at each moment are calculated. According to the Z score, linear instability index and threshold instability index of each feature at each moment, the comprehensive instability index of each feature at each moment is determined; According to the comprehensive instability index of each feature at each moment, the data at all moments are clustered to obtain the stability cluster center; According to the distance between the data at each moment and the stability cluster center, the stability evaluation result of the combustion process of the incinerator at each moment is determined.

2. The method according to claim 1, characterized in that Static characteristics of flame include average brightness and brightness standard deviation; dynamic characteristics of flame include average pulsation frequency, pulsation area ratio, average speed and average direction; According to the flame images collected at each moment, the static and dynamic features of the flame at each moment are extracted respectively, including: For the flame image collected at any moment, calculate the average brightness and brightness standard deviation of the flame image; Calculating an average pulsation frequency of the flame image based on the flame image and a preset frame flame image collected before the flame image; Calculate the pulsation area rate of the flame image based on the current flame image and the flame images of the two adjacent frames before and after; The speed of each pixel in the flame image is calculated using the optical flow method, and the average speed of all pixels in the flame image is taken as the average speed of the flame image; The velocity direction of each pixel in the flame image is calculated, and the average velocity direction of all pixels in the flame image is taken as the average direction of the flame image.

3. The method according to claim 1, characterized in that Calculate the linear instability index of the corresponding feature at each moment, including: For any feature, obtain the feature sequence at the current moment using the sliding window method; Perform linear fitting on the characteristic sequence by linear regression to determine the slope and goodness of fit of the linear fit; The absolute value of the product of the slope of the linear fit and the goodness of fit was determined as the linear instability index of the feature.

4. The method according to claim 1, wherein Calculate the threshold instability index of the corresponding feature at each moment, including: For any feature, if the value corresponding to the feature is greater than or equal to the lower threshold and less than or equal to the upper threshold, the threshold instability index of the feature is determined to be 0; When the value corresponding to the feature is greater than the upper limit of the feature threshold, or less than the lower limit of the feature threshold, the threshold instability index of the feature is determined according to the value of the feature, the upper limit of the feature threshold, and the lower limit of the feature threshold.

5. The method according to claim 4, characterized in that When the value corresponding to the feature is greater than the upper limit of the feature threshold, the calculation formula of the threshold instability index of the feature is: ； in, represents the threshold instability index, Indicates the value of the feature, represents the upper threshold of the feature, Indicates the lower limit of the feature threshold; When the value corresponding to the feature is less than the lower limit of the feature threshold, the calculation formula of the threshold instability index of the feature is: 。 6. The method according to claim 1, characterized in that Based on the Z score, linear instability index, and threshold instability index of each feature at each moment, the comprehensive instability index of each feature at each moment is determined, including: For any feature at each moment, the sum of the feature's Z score, linear instability index, and threshold instability index is used to determine the comprehensive instability index of the feature.

7. The method according to claim 1, characterized in that According to the comprehensive instability index of each feature at each moment, the data at all moments are clustered to obtain the stability cluster center, including: According to the comprehensive instability index of each feature at each moment, the data at all moments are clustered using a variety of different clustering algorithms to obtain the clustering results of each clustering algorithm; the clustering results include stable data clusters and unstable data clusters in the two-dimensional plane; Determine the best clustering algorithm based on the clustering results of each clustering algorithm; The cluster center of the stability data cluster of the best clustering algorithm is determined as the stability cluster center.

8. The method according to claim 7, characterized in that According to the distance between the data at each moment and the stability cluster center, the stability evaluation results of the incinerator combustion process at each moment are determined, including: Determine the incineration system stability index at each moment based on the distance between the data at each moment and the stability cluster center and the preset distance factor; At any moment, if the incineration system stability index is within a first preset range, the stability assessment result is determined to be that the combustion process of the incinerator is stable; If the incineration system stability index is within the second preset range, the stability assessment result is determined to be that the combustion process of the incinerator is relatively stable; If the incineration system stability index is within the third preset range, the stability assessment result is determined to be that the combustion process of the incinerator is unstable; all values ​​within the first preset range are greater than all values ​​within the second preset range, and all values ​​within the second preset range are greater than all values ​​within the third preset range.

9. The method according to claim 8, characterized in that The calculation formula of the incineration system stability index is: ； in, represents the stability index of the incineration system, represents the distance between the data point and the stability cluster center, Represents the distance factor.

10. A combustion process stability assessment device, characterized in that: include: The acquisition module is used to acquire data collected at multiple consecutive moments. The data at each moment includes the flame image of the incinerator during the combustion process, as well as status data and flue gas emission monitoring data; An extraction module is used to extract the static characteristics and dynamic characteristics of the flame at each moment based on the flame image collected at each moment; A calculation module is used to use the flame static characteristics and flame dynamic characteristics, as well as the state data and the flue gas emission monitoring data as features, and for any feature, calculate the Z score, linear instability index and threshold instability index of the corresponding feature at each moment; A comprehensive module is used to determine the comprehensive instability index of each feature at each moment based on the Z score, linear instability index and threshold instability index of each feature at each moment; The clustering module is used to cluster the data at all times according to the comprehensive instability index of each feature at each moment to obtain the stability cluster center; The determination module is used to determine the stability evaluation result of the combustion process of the incinerator at each moment according to the distance between the data at each moment and the stability cluster center.

Images