Incinerator system fault early warning method based on digital twinning

Abstract

The invention relates to the technical field of data processing, in particular to an incinerator system fault early warning method based on digital twinning, and the method comprises the steps: collecting the operation data of an incinerator; based on the distribution characteristics of the operation data in the data set coordinate system, obtaining the initial dependency degree of the target point on the neighbor point; fusing the deviation degree between the target point and the recent historical operation data and the fluctuation degree difference between the recent historical operation data and the long-term historical operation data to obtain the abnormal degree of the target point; obtaining the target dependency degree of the target point on the neighbor point according to the abnormal degree; and a self-adaptive K value is obtained through the target dependency degree of the target point on the neighbor point, the self-adaptive K value is used for monitoring the abnormity of the incinerator through FastABOD, and fault early warning is achieved in combination with digital twinning. The self-adaptive K value is obtained through the distribution characteristics of the data, and the limitation of using a fixed K value is broken through.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a method for incinerator system fault early warning based on digital twinning. BACKGROUND

[0002] As an industrial production device, the incinerator undertakes important functions such as waste treatment and energy recovery. The high-temperature, high-pressure operating environment and complex combustion process of the incinerator make it prone to failure. When the incinerator system has problems such as overheating and abnormal pressure during operation, it will usually cause equipment damage, and even cause safety accidents.

[0003] Currently, the integration of digital twinning technology and intelligent algorithms provides a new path for industrial equipment monitoring, and the use of digital twinning technology combined with FastABOD algorithm for incinerator fault judgment and early warning has gradually attracted attention. However, in related technologies, the FastABOD algorithm usually sets a fixed value, that is, the number of neighbor points, for each data point when calculating the anomaly score of each data point, and then analyzes the anomaly score of the data point based on the fixed value.

[0004] However, in actual application, the data distribution in different regions may have large differences, and using a fixed value for analysis has limitations. In low-density areas, data points are usually relatively isolated, with fewer surrounding data points and a long distance. If the fixed value set is small, the abnormality of the target point cannot be accurately captured. In high-density areas, data points are usually closely clustered together, with a short distance between them. They have high similarity in the local area, and only a small value is needed to effectively evaluate the abnormality of the data point. At this time, using a fixed value will increase the amount of calculation and produce unnecessary redundancy. As can be seen, this fixed value setting method restricts the applicability of the FastABOD algorithm for incinerator full-condition fault early warning. SUMMARY

[0005] To solve the above technical problems of using digital twinning technology combined with FastABOD algorithm for incinerator fault judgment and early warning, the FastABOD algorithm uses a fixed value for analysis. The present application provides a method for incinerator system fault early warning based on digital twinning, which comprises the following steps: Collecting operation data at several moments of the incinerator;With the operation data at the current moment as a target point, based on the distribution characteristics of the operation data at several moments in the data set coordinate system, the initial dependency of the target point on the neighbor point is obtained, the neighbor point is other data points distributed near the target point;With the data point at the immediately adjacent continuous previous moment of the current moment as the first data segment, and the data point at the immediately adjacent continuous previous moment of the current moment as the second data segment;Fusion The deviation degree of the target point and the operation data in the first data segment and the difference of the fluctuation degree of the operation data in the first data segment and the second data segment, to obtain the abnormal degree of the target point;According to the product of the abnormal degree of the target point and the initial dependency of the target point on the neighbor point, the target dependency of the target point on the neighbor point is obtained;The fixed value in the FastABOD algorithm is corrected through the target dependency of the target point on the neighbor point, and the adaptive value of the target point is obtained, and the adaptive value of the operation data at several moments on the neighbor point is obtained one by one, and the FastABOD algorithm is used for abnormal monitoring of the incinerator data, and the fault of the incinerator is warned in combination with the digital twin model.

[0006] The application is based on data sparsity characteristics and double period time sequence analysis, constructs the dynamic dependency of the target point on the neighbor point, breaks through the limitation of the fixed value of the traditional FastABOD algorithm, and can automatically select the adaptive number of neighbor points according to the neighborhood density characteristics, so as to increase the number of neighbor points in the low density area, capture more potential abnormal information, and reduce the number of neighbor points in the high density area, avoid calculation redundancy and improve detection efficiency. At the same time, combined with the physical mechanism verification function of the digital twin model, a double protection mechanism combining statistical anomaly recognition and mechanism deviation checking is formed, which effectively reduces the false alarm rate and accurately locates the fault type. The application can capture the abnormal precursors of the key operation data of the incinerator in real time, trigger the fault warning in advance, provide intelligent support for stable operation of the equipment, reduce the non-scheduled downtime, and reduce the operation and maintenance cost.

[0007] Preferably, the initial dependency of the target point on the neighbor point satisfies the relationship: ; Wherein, is the initial dependency of the operation data at the i th moment on the neighbor point, is the preset number of neighbor points of the target point, is the distance between the operation data at the i th moment and the i th neighbor point, is the distance between the operation data at the i The average distance between the running data at each time point and all neighboring points. It is the average distance between all data points in the dataset's coordinate system. It is the standard normalized function.

[0008] This invention calculates the distance between a target point and preset neighbor points, combines the deviation between the average distance between the target point and its neighbors and the global average distance, and performs two normalizations to eliminate dimensional interference, accurately characterizing the density distribution of target points in the dataset coordinate system; it also transforms the spatial distribution into a quantized initial dependency for subsequent adaptive adjustment. This lays the foundation for the FastABOD algorithm to dynamically adapt the number of neighbor points it calculates to the data distribution, breaking through the limitations of fixed values. To overcome the limitations of current values, we need to improve the accuracy and efficiency of incinerator anomaly detection.

[0009] Preferably, the difference in the degree of fluctuation of the running data in the first data segment and the second data segment is quantified by the difference between the interquartile range of the running data in the first data segment and the interquartile range of the running data in the second data segment, wherein the interquartile range is used to characterize the discrete fluctuation level of the running data in each data segment.

[0010] This invention leverages the interquartile range's ability to characterize data dispersion fluctuations. By calculating the difference in the interquartile range between the first and second data segments, it captures the variation in dispersion of operational data across two time periods. This difference reflects the difference in the dispersion trend of the recent data segment relative to the long-term data segment. It provides temporal-series fluctuation pattern support for subsequent assessment of anomalies when merging deviations, enabling anomaly detection to combine data dispersion trend variations for more accurate identification of potential anomalies in incinerator operation.

[0011] Preferably, the acquisition of the difference in the degree of fluctuation of the running data in the first data segment and the second data segment includes: acquiring the first-order difference sequence of the first data segment and the first-order difference sequence of the second data segment; and acquiring the difference in the degree of fluctuation of the running data in the first data segment and the second data segment by calculating the absolute value of the difference between the variance of the first-order difference sequence of the first data segment and the variance of the first-order difference sequence of the second data segment.

[0012] Preferably, the deviation between the target point and the running data in the first data segment is obtained by calculating the absolute value of the difference between the maximum value of the running data in the first data segment and the target point.

[0013] Preferably, the adaptive The values ​​satisfy the following relation: ; in, It is the first Adaptation of runtime data at each moment value, It is the initial preset fixed value, It is the first The degree of dependency of runtime data on neighboring points at each time step. It is the floor symbol. It performs a rounding operation. yes The preset lower limit value.

[0014] This invention dynamically correlates target dependency with initial fixed This value enables dynamic adjustment of the number of neighboring points. First, let's consider... A basic association is established, then numerical adaptability is optimized through rounding, and finally, reasonableness is ensured by rounding down and setting a preset lower limit. The number of neighbor points is dynamically adjusted according to the target point's dependency; the higher the target dependency, the more neighbor points are added to capture potential anomalies; the lower the target dependency, the fewer neighbor points are added to avoid computational redundancy. This mechanism breaks through the traditional fixed... Overcoming the limitations of traditional values, this system precisely adapts to the differences in incinerator data distribution, significantly improving the efficiency and accuracy of anomaly detection.

[0015] Preferably, the second data segment includes the first data segment. .

[0016] Preferably, the operating data includes incinerator temperature data and pressure data.

[0017] Preferably, the adaptive data at the specified time points are obtained sequentially. The FastABOD algorithm is used to monitor incinerator data for anomalies, and a digital twin model is used to provide early warnings of incinerator malfunctions, including: adaptive data based on each time step. The system calculates the anomaly score of the incinerator operation data at each moment; when the anomaly score is greater than a preset anomaly score threshold, the operation data at the corresponding moment is marked as anomaly data; the operation data marked as anomaly data is input into the digital twin model to determine whether it belongs to a fault and trigger an alarm.

[0018] Preferably, the construction of the digital twin model includes: using the current operating data as real-time data and the operating data before the current time as historical data, establishing a digital twin model by combining the real-time data and historical data with the physical structure parameters and process mechanism of the incinerator; using historical data as a benchmark, correcting the parameter deviations in the digital twin model, mapping the real-time data into the digital twin model, updating the boundary conditions of the digital twin model, so that the digital twin model simulates the operating state of the incinerator; receiving the input operating data, calculating the deviation between the actual state of the incinerator corresponding to the operating data and the state simulated by the digital twin model, so as to match the fault type and trigger an alarm.

[0019] The present application optimizes the value acquisition mode in the FastABOD algorithm , so that it can more accurately identify anomalies based on data distribution characteristics and accurately capture discrete abnormal points. The digital twin model verifies the anomaly based on the simulation of the real operation logic of the incinerator. The combination of the two forms a complement: the FastABOD algorithm is responsible for quickly screening potential anomalies, and the digital twin model completes the verification from the mechanism level, retaining the efficiency of the algorithm and excluding false positives with the help of physical laws, thereby significantly improving the accuracy of fault detection, effectively reducing the false positive rate, and achieving accurate positioning of faults.

[0020] The present application has the following advantages: Based on data density characteristics and double-period time series analysis, the present application constructs the dynamic dependency of target points on neighbor points, breaking through the limitations of traditional FastABOD algorithms using fixed values. The number of neighbor points can be automatically selected according to the neighborhood density characteristics, thereby increasing the number of neighbor points in low-density areas to capture more potential abnormal information, and reducing the number of neighbor points in high-density areas to avoid computational redundancy and improve detection efficiency. At the same time, by calculating the difference between the quartile ranges of the first and second data segments, the dispersion change of the running data in the two periods is captured, providing support for the fluctuation rules in the time series dimension when evaluating the degree of anomaly based on the subsequent fusion of the degree of deviation. Finally, combining FastABOD and digital twin models improves the accuracy of fault judgment and alarm precision. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 The present application provides a flowchart of an incinerator system fault early warning method based on digital twinning. DETAILED DESCRIPTION

[0022] The present application provides an incinerator system fault early warning method based on digital twinning, as shown in Figure 1 , the method comprises steps S100-S600: Step S100, collect the running data of the incinerator at several time points.

[0023] It should be noted that the core function of the incinerator is to achieve harmless treatment of waste through high-temperature combustion, and the temperature in the furnace directly reflects the combustion efficiency and reaction state. Temperature data is a key indicator for determining whether the incinerator combustion state is stable, whether there is overheating or combustion failure. The pressure data in the incinerator can reflect the stability of the airflow in the furnace in real time, and is an important basis for predicting potential problems such as flue blockage and fan failure. Therefore, the present application selects temperature data and pressure data as key monitoring parameters for fault early warning.

[0024] Specifically, a temperature sensor and a pressure sensor are arranged at the sampling point, and the temperature data and the pressure data of the incinerator at several time points are continuously collected by setting a sampling frequency, which are collectively referred to as operation data. The sampling frequency can be set to 10 times per second, and can be set according to requirements.

[0025] Up to now, the operation data of the incinerator at several time points is obtained.

[0026] Step S200, taking the operation data at the current time as a target point, based on the distribution characteristics of the operation data at several time points in the data set coordinate system, the initial dependence of the target point on the neighbor point is obtained, and the neighbor point is other data points distributed around the target point.

[0027] It should be noted that the FastABOD algorithm is a fast angle-based outlier detection algorithm, which can greatly reduce the calculation cost by sampling, can process large-scale data sets, and is suitable for unlabeled outlier detection scenarios. Based on these advantages, the present application adopts the FastABOD algorithm to realize the fault early warning of the incinerator system. However, when selecting neighbor points, the algorithm usually uses a fixed value, which has limitations in processing high-density and low-density areas, so the present application improves the FastABOD algorithm for this limitation.

[0028] Specifically, taking the operation data at the current time as a target point, if the target point is relatively isolated in the data set coordinate system, it is difficult to find enough neighbor points, at this time, the data based on a few neighbor points cannot reflect the overall structure of the region where it is located. Therefore, in the low-density area, a value that is more neighbor points is needed to reflect the position of the target point in the data set and improve the stability of anomaly detection, and the dependence of the target point on the neighbor point in this area is greater. If the target point is relatively concentrated with other data points in the data set coordinate system, it is not easy to be misjudged as an anomaly. Therefore, a smaller value can be used to evaluate whether the target point is abnormal, and the dependence of the target point on the neighbor point in the high-density area is smaller.

[0029] Therefore, the value of the target point in the calculation of the anomaly score can be optimized by the density characteristics of the data points in the data set coordinate system.

[0030] Specifically, according to the above logic, the initial dependence of the target point on the neighbor point satisfies the relationship: ; Wherein, is the initial dependence of the operation data at the i th time on the neighbor point, is the preset number of neighbor points of the target point, is the running data at the th moment and the distance to the th neighbor point, is the average of the distance of the running data at the th moment to all neighbor points, is the average of the distance between all data points in the data set coordinate system, is a standard normalization function.

[0031] In the formula, is the sum of the distance of the running data at the th moment to its preset neighbor points, the greater the value, the more the running data at the th moment is in a low-density area, and more neighbor points are needed to reflect the position of the target point in the data set, so the greater the initial dependence on neighbor points calculated. In the formula, is the difference between the average distance of the running data at the th moment to all neighbor points and the average distance between all data points in the data set coordinate system, the greater the value, the higher the degree of relative isolation of the running data at the th moment in the data set coordinate system, so the initial dependence of the th running data on neighbor points should also be greater.

[0032] In addition, the data set can be set to contain 500 data points, and can also be set according to actual needs. The number of preset neighbor points U of the target point can be set to 50, and can also be set according to actual needs.

[0033] At this point, the initial dependence of the target point on the neighbor points is obtained.

[0034] Step S300, the data points of the immediately preceding th moment of the current moment as the first data segment, and the data points of the immediately preceding th moment of the current moment as the second data segment; fuse the deviation degree of the target point and the running data in the first data segment and the difference in the fluctuation degree of the running data in the first data segment and the second data segment to obtain the abnormal degree of the target point.

[0035] It should be noted that the above steps are based on the sparsity characteristics of the data points around the target point to obtain the initial dependence of the target point on the neighbor points, but only the position and density characteristics of the target point in the data set coordinate system are not enough to fully evaluate the demand of the target point for value.

[0036] The present application considers that the collected temperature data and pressure data are time series data, which may have significant fluctuations at different time points, and these fluctuations may be related to environmental conditions or potential faults. Normal fluctuations need to be further distinguished from fault precursors through time series characteristics. In particular, when the incinerator fails, there will be more data points with special temperature and pressure values, which may be more clustered and may affect the selection of the value and the accuracy of the anomaly detection result. Therefore, it is also necessary to analyze the value performance characteristics of the target point in the respective time series of the operation data, that is, the temperature data and the pressure data. The more special the performance is, the more likely the target point is to be abnormal data, and more attention needs to be given to it when calculating its anomaly score, more neighbor points need to be set, that is, a larger value needs to be set for it.

[0037] Specifically, if the temperature data and pressure data of the target point are special in the respective time series of the value performance, the target point deviates from the historical data to a higher degree, and the fluctuation degree difference of the historical data is more obvious. Therefore, the abnormality of the target point can be measured by the deviation degree and the fluctuation degree difference.

[0038] It should be noted that to quantify these two indicators, pre-operation is also needed to define the reference historical data segment.

[0039] Specifically, it is realized by selecting recent historical data and long-term historical data. The data points of the immediately adjacent continuous previous time points of the current time are taken as the first data segment, and the data points of the immediately adjacent continuous previous time points of the current time are taken as the second data segment. The second data segment contains the first data segment, . The abnormality of the target point can be evaluated in combination with the two historical data segments, which can improve the accuracy of the abnormality degree judgment.

[0040] For example, 50 data points immediately before the current time are selected as the first data segment, and 600 data points immediately before the current time are selected as the second data segment. Based on the sampling frequency set in the foregoing, which is 10 times per second, if the initial data points are insufficient, one minute of operation data can be pre-collected to meet the construction requirements of the two data segments.

[0041] After the pre-operation is completed, the next step is to explain how to quantify these two indicators.

[0042] Regarding the fluctuation degree difference of the historical data, the interquartile range can be used to quantify it. The interquartile range is a statistical quantity that describes the dispersion degree of 50% of the data in the data set, and is usually used to identify outliers and measure the distribution characteristics of the data.

[0043] Specifically, based on this characteristic, the application is realized by the difference between the interquartile range of the running data of the first data segment and the interquartile range of the running data of the second data segment, wherein the interquartile range is used to characterize the discrete fluctuation level of the running data in each data segment. The calculation of the interquartile range is a prior art, and will not be described in detail here.

[0044] In addition, the fluctuation difference of the historical data can also be quantified by the variance of the time series data, and the actual implementation can be selected according to the needs.

[0045] Specifically, first, the first-order difference sequence of the first data segment and the first-order difference sequence of the second data segment are calculated; then, the fluctuation difference of the two data segments is obtained by calculating the absolute value of the difference between the variance of the first-order difference sequence of the first data segment and the variance of the first-order difference sequence of the second data segment. The absolute difference reflects the difference between the change amplitude of the recent historical data and the change amplitude of the long-term historical data, and is suitable for capturing the abnormality of the mutation frequency of the device.

[0046] Regarding the deviation degree of the target point relative to the historical data, since the incinerator failure is mostly overheating or excessive pressure, only the maximum value needs to be considered. Specifically, the absolute value of the difference between the maximum value of the running data in the first data segment and the target point can be obtained.

[0047] The above describes two factors affecting the abnormality degree of the target point, and the following describes how to integrate the two indicators to obtain the abnormality degree of the target point.

[0048] It should be noted that there are limitations in analyzing the two indicators separately: if only the deviation degree of the target point relative to the historical data is considered, when the deviation degree of the target point is large but the fluctuation difference is small, it means that the historical data is regular and the extreme value is rare, and the abnormal signal reflected by the deviation degree is more alarming when it breaks the regularity. If only the fluctuation difference of the historical data is considered, when the fluctuation difference is large but the deviation degree is small, it means that the historical data is naturally discrete, and small fluctuations are normal, and the abnormal risk is lower at this time. Therefore, multiplying the two can depict the possibility of the occurrence of special values and the actual strength of the special values, and more comprehensively reflect the abnormal risk of the incinerator running data.

[0049] Specifically, in order to realize the above logic, taking temperature data as an example, the target dependence of the temperature data on the neighbor point satisfies the relationship: ; Wherein, is the abnormality degree of the temperature data at the i-th moment on its corresponding time series, is the temperature data at the i-th moment, is the temperature data at the i-th moment, is the temperature data at the i-th moment, is the temperature data at the i-th moment, The maximum value of the temperature data at each moment in the first data segment. This is a very small value, which can be set to 0.001, or can be set according to needs, to prevent... =0; It is the first The interquartile range of the temperature data at each moment in the dataset consisting of all data in the first data segment. It is the first The interquartile range of the temperature data at each moment in the dataset consisting of all data in the second data segment. It is the standard normalized function. It is an absolute value. The degree of fluctuation in historical data can be calculated using the interquartile range or the variance of the difference series.

[0050] In this formula, The larger it is, the more it indicates the number of... The more unique the temperature data at a given moment is in terms of its temporal sequence, the more unique the corresponding numerical value. The larger the value, the more likely it is to be the first. The numerical distribution of the temperature data at time t is more discrete in the first reference segment compared to the numerical distribution in the second reference segment, which indicates that the temperature data at time t is... The greater the probability that a temperature data point at a given time will have an unusual value, the more unusual the corresponding value will be.

[0051] At this point, we have obtained the current operational data, which is the degree of anomaly at the target point.

[0052] Step S400: Obtain the target dependency of the target point on its neighboring points based on the product of the anomaly degree of the target point and the initial dependency of the target point on its neighboring points.

[0053] It should be noted that the more unusual the temperature and pressure data of the target point are in their respective time series, the greater the likelihood that the target point is a potential outlier. Therefore, it needs to be given more attention when calculating its outlier score, and more neighboring points should be set; that is, a larger set of neighboring points should be assigned to it. value.

[0054] Preferably, the target dependency of the target point on its neighboring points satisfies the following relationship: ; in, It is the first The degree of dependency of runtime data on neighboring points at each time step. It is the first The initial dependency of the runtime data on neighboring points at each time step. It is the first The degree of anomaly in the temperature data at each moment in its corresponding time series. It is the first The degree of anomaly in the pressure data at a given moment within its corresponding time series is calculated using the same logic as that for temperature data, and will not be elaborated upon here. This is an adjustment coefficient for the target point's dependency on its neighboring points, used to adapt to subsequent... Value adaptive, It can be set to 0.5 to adjust the target dependency of the target point on its neighboring points to a range. , The size can also be set according to requirements.

[0055] In this formula, The larger the value, the more likely it is to be the first. When analyzing the density characteristics of surrounding data points in the dataset coordinate system at a given time step, the higher the initial dependence on neighboring points, the greater the corresponding target dependence on neighboring points. In the formula... The larger the value, the more likely it is to be the first. The more unusual the numerical performance of the temperature and pressure data at each time point, the higher the probability that the target point belongs to potential outliers, which also means that the... The more isolated the runtime data is within the dataset coordinate system at a given time point, the greater its credibility. In this case, calculating the anomaly score requires a larger... The value, that is, more neighboring points are needed to reflect the location of the target point in the dataset, thereby improving the stability of anomaly detection. Therefore, the corresponding value is... The operational data at each time point will also have a stronger dependence on the target of neighboring points.

[0056] At this point, the target dependency of the target point on its neighboring points has been obtained.

[0057] Step S500: Correct the fixed parameters in the FastABOD algorithm by adjusting the target dependency of the target point on its neighboring points. The value is used to obtain the adaptive value of the target point. value.

[0058] It should be noted that the above steps obtain the target dependency of the target point on its neighboring points. The greater the target dependency, the more isolated the target point is in the dataset coordinate system, and the more unusual the numerical performance of its corresponding two dimensions in their respective time series. Therefore, when calculating the anomaly score of the incinerator's operating data, a larger value needs to be set. The value allows the algorithm to gain a more comprehensive understanding of the target point's location within the entire dataset, improving anomaly detection accuracy. Conversely, the lower the target point's dependence on its neighbors, the more clustered it is with other data points in the dataset's coordinate system, and the more normal the numerical performance of its corresponding two dimensions in their respective time series. Therefore, to improve the algorithm's computational efficiency, a smaller value can be set. value.

[0059] Specifically, based on the above logic, the adaptive target point The values ​​satisfy the following relation: ; in, It is the first Adaptation of runtime data at each moment value, It is the initial preset fixed value, It is the first The degree of dependency of runtime data on neighboring points at each time step. It rounds down. It performs rounding to ensure the result is an integer, which conforms to... The actual value requirements, yes The preset lower limit value can be set to 1 or set according to requirements.

[0060] In this formula, The larger the value, the more isolated the target point is, and the higher its dependence on neighboring points. The larger the value, the more neighboring points it has, which can comprehensively characterize its position in the dataset and improve the accuracy of anomaly identification. The smaller the value, the more clustered the data points are, and the lower the target dependence on neighboring points. The calculated value is... The smaller the value, the fewer neighbor points are obtained, which reduces the amount of computation and improves efficiency while ensuring the basic effect.

[0061] At this point, the adaptive target point has been obtained. value.

[0062] Step S600: Obtain the adaptive data of neighbor points at several time points. The FastABOD algorithm is used to monitor incinerator data for anomalies, and a digital twin model is used to provide early warning of incinerator malfunctions.

[0063] It should be noted that, based on the aforementioned steps, the adaptive calculation of anomaly scores can be performed by acquiring the runtime data at each time point. This addresses the issue of using a fixed value in the FastABOD algorithm. The value has the problem of limitation.

[0064] Specifically, based on the calculated adaptive value, the abnormal score of each incinerator operation data is calculated by the FastABOD algorithm. When the abnormal score is greater than the abnormal threshold, the data point is determined as an abnormal data point, and the abnormal threshold can be set to 10, or can be set according to requirements.

[0065] It should be noted that digital twinning is a technology that virtually copies physical entities, processes or systems and is real-time associated with the physical world. Through sensors, the running data of physical entities is collected, combined with simulation, modeling and data analysis technology, and a digital model that can dynamically map, simulate and predict the whole life cycle state of physical entities is constructed in virtual space. The present application combines digital twinning model and FastABOD algorithm to realize fault early warning of incinerator system.

[0066] Specifically, the running data at the current time is taken as real-time data, and the running data before the current time is taken as historical data. The digital twinning model is established by using real-time data and historical data in combination with physical structure parameters and process mechanism of the incinerator. Based on the historical data, the parameter deviation in the digital twinning model is corrected, the real-time data is mapped into the digital twinning model, and the boundary conditions of the digital twinning model are updated, so that the digital twinning model simulates the running state of the incinerator.

[0067] In actual use, when the FastABOD algorithm determines that a data point is abnormal, the running data corresponding to the data point is input into the digital twinning model, the boundary conditions of the model are updated in real time, and the running state of the virtual model is synchronized with the physical incinerator system in real time. By comparing the normal state simulated by the virtual model with the real-time running data of the physical equipment, the deviation amount is calculated: when the deviation amount is within the preset threshold range, it is determined that the operation is normal; if the deviation amount exceeds the threshold, the real-time deviation characteristics are compared with the deviation patterns of the historical abnormal data, and the highest matching degree is the suspected fault type, thereby triggering the early warning. The threshold range can be set to temperature deviation , pressure deviation , and the threshold can also be dynamically adjusted according to the load and working condition type of the incinerator.

[0068] In the present application, the FastABOD algorithm identifies abnormalities based on statistical characteristics, and the digital twinning model verifies abnormalities based on physical mechanism. The combination of the two improves the accuracy of fault detection and reduces the false alarm rate of the alarm.

[0069] The above are preferred embodiments of the present application, which do not limit the protection scope of the present application, therefore: any equivalent changes made on the structure, shape, principle of the present application should be covered within the protection scope of the present application.

Claims

1. A method for incinerator system failure early warning based on digital twinning, characterized in that, The method comprises the steps of: collecting operation data of the incinerator at several time points; taking the operation data at the current time point as a target point, obtaining an initial dependency of the target point on neighbor points based on distribution characteristics of the operation data at the several time points in a data set coordinate system, the neighbor points being other data points distributed around the target point; The immediate preceding consecutive times of the current moment The data points at each time point are taken as the first data segment, and the data points immediately preceding the current time point are taken as the next data segment. The data points at each time point are the second data segment; the deviation degree between the target point and the running data in the first data segment, as well as the difference in the fluctuation degree of the running data in the first data segment and the second data segment, are fused to obtain the anomaly degree of the target point; obtaining a target dependency of the target point on the neighbor points according to a product of an abnormality degree of the target point and the initial dependency of the target point on the neighbor points; The target point is used to correct the fixed value in the FastABOD algorithm of the neighbor point target dependence degree, to obtain the adaptive value of the target point value ​ Adaptive acquisition of running data of several time points for neighbor points one by one The value, using FastABOD algorithm for incinerator data anomaly monitoring, combined with digital twin model for incinerator fault warning.

2. The digital-twin-based incinerator system failure early warning method according to claim 1, characterized in that, the initial dependency of the target point on the neighbor points satisfies a relationship: ； wherein, is the initial dependency of the running data of the th time instant on the neighbor points, is the number of neighbor points preset for the target point, is the distance between the running data of the th time instant and the th neighbor point, is the average distance between the running data of the th time instant and all neighbor points, is the average distance between all data points in the data set coordinate system, is a standard normalization function. 3.The digital-twin-based incinerator system failure early warning method of claim 1, wherein a difference in fluctuation degrees of the operation data in the first data segment and the second data segment is quantified by a difference between a quartile range of the operation data in the first data segment and a quartile range of the operation data in the second data segment, wherein the quartile range is used to represent a discrete fluctuation level of the operation data in each data segment. 4.The digital-twin-based incinerator system failure early warning method of claim 1, wherein The obtaining of the difference in fluctuation degrees of the operation data in the first data segment and the second data segment comprises: obtaining a first-order difference sequence of the first data segment and a first-order difference sequence of the second data segment; obtaining the difference in fluctuation degrees of the operation data in the first data segment and the second data segment by calculating an absolute value of a difference between a variance of the first-order difference sequence of the first data segment and a variance of the first-order difference sequence of the second data segment. 5.The digital-twin-based incinerator system failure early warning method of claim 1, wherein, The deviation degree of the target point from the operation data in the first data segment is obtained by calculating an absolute value of a difference between a maximum value of the operation data in the first data segment and the target point. 6.The digital-twin-based incinerator system failure warning method of claim 1, wherein The adaptive The values satisfy the relationship: ； wherein is the adaptive value of the operating data at the nth time instant, is the initial preset fixed value, is the target dependency of the operating data at the nth time instant on the neighbor point, is the floor symbol, is the rounding operation, is a preset lower limit value of the value. 7.The digital-twin-based incinerator system failure warning method of claim 1, wherein The second data segment contains the first data segment, . 8.The digital-twin-based incinerator system failure early warning method of claim 1, wherein, The operation data comprises temperature data and pressure data in the incinerator. 9.The digital-twin-based incinerator system failure warning method of claim 1, wherein The adaptive values of the several time points are acquired one by one The application discloses a method for monitoring and early warning of incinerator faults. Adaptation based on each time instant a value, to calculate an anomaly score for the incinerator operating data at each time instant; When the abnormality score is greater than a preset abnormality score threshold, the operation data at the corresponding time point is marked as abnormal data; the operation data marked as abnormal data is input into a digital twin model to determine whether it belongs to a fault to trigger an alarm. 10.The digital-twin-based incinerator system failure early warning method of claim 1, wherein The construction of the digital twin model comprises: taking the operation data at the current time point as real-time data and taking the operation data before the current time point as historical data, the digital twin model is established by combining the real-time data and the historical data with physical structure parameters and process mechanisms of the incinerator; taking the historical data as a reference, parameter deviations in the digital twin model are corrected, the real-time data is mapped into the digital twin model, boundary conditions of the digital twin model are updated, and the digital twin model simulates the running state of the incinerator; the input operation data is received, a deviation between an actual state of the incinerator corresponding to the operation data and a state simulated by the digital twin model is calculated, a fault type is matched, and an alarm is triggered.

Images