Fuel intelligent monitoring and early warning system and method

Abstract

The invention provides an intelligent fuel monitoring and early warning system and method. Relates to the technical field of monitoring and early warning. The system comprises the following steps: determining and deploying fuel monitoring sensors according to fuel monitoring indexes; acquiring fuel monitoring data, processing the data and transmitting the data to a fuel monitoring and early warning platform; a fuel intelligent monitoring and early warning algorithm and a data mining model are constructed to perform data analysis on the received data of the fuel monitoring and early warning platform, a data abnormal value is determined, and when the data abnormal value exceeds a threshold value of a preset index abnormal early warning threshold value system, real-time early warning is executed; intelligent monitoring and early warning of fuel data are effectively realized, and standard management of intelligent fuel monitoring is ensured.

Description

Technical Field

[0001] The present invention relates to the field of monitoring and early warning technology, and in particular to a fuel intelligent monitoring and early warning system and method. Background Art

[0002] With the rapid development of society, fuel data continues to increase, fuel abnormality data also continues to increase, and the mutual influence relationship between fuel data is becoming more and more complex. Manual abnormal judgment of fuel data is inefficient and has low judgment accuracy, which is not in line with the intelligent fuel management. In addition, existing business needs are constantly changing, while fuel monitoring indicators are fixed, which cannot ensure the standardization of fuel monitoring indicator management and cannot achieve intelligent and continuous monitoring and management of fuel.

[0003] Therefore, the present invention provides a fuel intelligent monitoring and early warning system and method. Summary of the invention

[0004] The present invention provides a fuel intelligent monitoring and early warning system and method, which are used to determine and deploy fuel monitoring sensors through fuel monitoring indicators; obtain fuel monitoring data for data processing and transmit it to a fuel monitoring and early warning platform; construct a fuel intelligent monitoring and early warning algorithm and a data mining model to perform data analysis on the received data of the fuel monitoring and early warning platform, determine data abnormal values, and execute real-time early warning when the data abnormal value exceeds the threshold of a preset indicator abnormal early warning threshold system; effectively realize the intelligent monitoring and early warning of fuel data, and ensure the standardized management of fuel intelligent monitoring.

[0005] The present invention provides a fuel intelligent monitoring and early warning system, comprising: Monitoring deployment module: used to determine the fuel monitoring sensor type and sensor deployment location according to the fuel monitoring indicators and perform corresponding sensor deployment; Data processing module: used to obtain fuel monitoring data based on deployed sensors and perform data processing, and transmit the processed fuel monitoring data to the fuel monitoring early warning platform; Analysis and early warning module: used to construct a fuel intelligent monitoring and early warning algorithm and a data mining model to analyze the data received by the fuel monitoring and early warning platform, determine data anomalies, and execute real-time early warning when the data anomaly exceeds the threshold of the preset indicator abnormal early warning threshold system.

[0006] According to the present invention, a fuel intelligent monitoring and early warning system, a monitoring deployment module, includes: A fuel monitoring indicator unit, used to determine the fuel monitoring indicator according to the preset fuel monitoring target and historical fuel monitoring data; A sensor unit, used to determine the type of fuel monitoring sensor and the sensor deployment location according to the fuel monitoring index, and dynamically monitor and control the number of various sensors monitored according to historical fuel monitoring data; A monitoring and deployment unit, used to perform corresponding sensor deployment according to the sensor deployment position and the dynamic monitoring and control result; The deployed sensors are monitored and calibrated. When the monitoring output value of the sensor is consistent with the monitoring calibration value, it is determined that the deployment of the corresponding sensor is completed.

[0007] According to a fuel intelligent monitoring and early warning system provided by the present invention, a fuel monitoring indicator unit includes: The fuel monitoring indicator analysis framework block is used to construct a fuel monitoring indicator analysis framework based on the preset fuel monitoring target; A fuel monitoring indicator block is used to obtain fuel supply, fuel consumption, fuel storage, fuel quality and fuel combustion data based on historical fuel monitoring data and generate corresponding initial fuel monitoring indicators; The initial fuel monitoring indicator is classified and processed according to the preset fuel monitoring target and analyzed and processed according to the fuel monitoring indicator analysis framework, and when it is monitored that the initial fuel monitoring indicator meets the fuel monitoring requirement, the corresponding initial fuel monitoring indicator is determined to be a fuel monitoring indicator; Otherwise, the corresponding indicators will be eliminated.

[0008] According to the present invention, a fuel intelligent monitoring and early warning system, a data processing module, includes: A data integration unit, used for integrating and processing the fuel monitoring data acquired by the sensor within the current cycle time period according to the data upload cycle; A data processing unit, used for preprocessing the fuel monitoring data and performing data conversion processing according to the data standard of the fuel monitoring early warning platform; When the data conversion process is completed, the data is compressed and stored; A data transmission unit, used to establish a stable connection between the data storage area and the fuel monitoring and early warning platform and to encrypt and transmit the processed fuel monitoring data to the fuel monitoring and early warning platform; When the data received by the fuel monitoring early warning platform is consistent with the fuel monitoring data after the data processing, it is determined that the data transmission is completed; Otherwise, retransmit the data.

[0009] According to the present invention, a fuel intelligent monitoring and early warning system, an analysis and early warning module, includes: A data mining model unit, used to obtain historical abnormal data based on historical fuel monitoring data, and select historical abnormal data that has data correlation with the fuel monitoring index to construct a historical abnormal data set; Reorder the historical abnormal data set according to the monitoring period to obtain the monitoring accuracy of the fuel monitoring indicator, and divide the reordered historical abnormal data set into historical abnormal data subsets of the monitoring accuracy value according to the monitoring accuracy value; Performing data mining on the historical abnormal data subset to obtain a feature vector of the historical abnormal data subset; Performing superposition statistics on the characteristic vectors of each historical abnormal data subset, determining the first data mining value of the historical abnormal data set, and constructing a data mining model; A data mining unit, configured to input the received data into a data mining model, determine a second data mining value of the received data, and when the second data mining value is not lower than the first data mining value, determine that the data mining model performs effective data mining on the received data; Otherwise, it is determined that the data mining model performs invalid data mining on the received data and performs sequential data mining on an indicator-by-indicator basis according to the fuel monitoring indicators; A fuel intelligent monitoring and early warning algorithm unit, used to construct a fuel intelligent monitoring and early warning algorithm based on the data mining model and historical fuel monitoring data; An early warning threshold unit, used to construct a preset indicator abnormal early warning threshold system according to the fuel monitoring indicator; Obtaining a threshold of a preset indicator abnormality warning threshold system, determining a threshold correlation between the received data and the threshold of the preset indicator abnormality warning threshold system according to historical fuel monitoring data, dynamically adjusting the threshold, and determining a dynamically adjusted threshold of the preset indicator abnormality threshold system; A fuel monitoring unit, configured to perform data analysis on the received data of the fuel monitoring and early warning platform according to the data mining model and the fuel intelligent monitoring and early warning algorithm, and determine data abnormal values ​​of the received data; ; Among them, F represents the data outlier of the received data; y1 represents the number of valid data mining in the received data; y2 represents the number of sequential data mining by indicator in the received data; Indicates the number of received data that have a threshold correlation with the j1th fuel monitoring indicator in the received data; represents the fuel monitoring value of the i1th received data in the j1th fuel monitoring indicator; Indicates the dynamic adjustment threshold of the j1th fuel monitoring indicator in the preset indicator abnormal threshold system; represents the threshold value of the j1th fuel monitoring indicator in the preset indicator abnormal threshold system; m1 represents the number of fuel monitoring indicators in the preset indicator abnormal threshold system; When the data abnormal value of the received data exceeds the dynamically adjusted threshold of the preset indicator abnormal warning threshold system, it is determined that there is abnormal received data in the received data and the abnormal received data is marked; An abnormal data impact unit, used for randomly selecting abnormal received data and other received data when it is determined that there is abnormal received data in the received data, and determining the data impact of the randomly selected abnormal received data on other received data according to the fuel intelligent monitoring and early warning algorithm; When the data influence degree of the randomly selected abnormal received data on other received data is not less than the preset influence degree, the randomly selected abnormal received data is determined to be the strong influence data corresponding to the other received data, and a strong influence label is added; Otherwise, determining that the randomly selected abnormal received data is weakly affected data corresponding to the other received data, and adding a weakly affected label; When there is no data influence between the randomly selected abnormal received data and other received data, the randomly selected abnormal received data and the corresponding other received data are determined to be non-influenced data, and a non-influence label is added; The receiving data relation unit is used to segment the fuel combustion process, and divide the receiving data corresponding to the monitoring data of the fuel unburned section into a first type of receiving data, and divide the receiving data corresponding to the monitoring data of the fuel burning section into a second type of receiving data; Determine the mutual influence relationship between the first type of received data and the second type of received data according to the data mining model; An abnormality locating unit, configured to locate abnormal origin data of the abnormal reception data according to the influence label and the mutual influence relationship in combination with the abnormal reception data; The real-time warning unit is used to call corresponding alarm data from the alarm database for real-time warning according to the abnormal origin data.

[0010] According to the present invention, a fuel intelligent monitoring and early warning system, a real-time early warning unit, comprises: An exception analysis block is used to analyze the exception origin data and determine the exception type of the exception origin data; The abnormal warning block is used to call the corresponding abnormal type alarm database according to the abnormal type and perform abnormal matching. When the abnormal matching is successful, the corresponding alarm data is called for real-time warning and the abnormal alarm data is recorded; Otherwise, new alarm data is generated for real-time warning and the alarm data is stored.

[0011] A fuel intelligent monitoring and early warning system provided by the present invention also includes: A visualization module, for visually displaying fuel monitoring indicators, the received data, abnormal origin data and alarm data; The prediction and warning module is used to predict the supply, consumption and storage of fuel based on the current period fuel monitoring data and historical fuel monitoring data, and to perform prediction and warning in combination with the indicator abnormal warning threshold system.

[0012] The present invention provides a fuel intelligent monitoring and early warning method, comprising: Step 1: Determine the type of fuel monitoring sensor and the sensor deployment location based on the fuel monitoring indicators and deploy the corresponding sensors; Step 2: Obtain fuel monitoring data from the deployed sensors and process the data, and transmit the processed fuel monitoring data to the fuel monitoring early warning platform; Step 3: Construct a fuel intelligent monitoring and early warning algorithm and a data mining model to perform data analysis on the received data of the fuel monitoring and early warning platform, determine data anomalies, and execute real-time warning when the data anomaly exceeds the threshold of the preset indicator abnormal warning threshold system.

[0013] Compared with the prior art, the present invention has the following beneficial effects: Determine and deploy fuel monitoring sensors based on fuel monitoring indicators; obtain fuel monitoring data for data processing and transmit to the fuel monitoring early warning platform; construct a fuel intelligent monitoring and early warning algorithm and a data mining model to analyze the data received by the fuel monitoring and early warning platform, determine data anomalies, and execute real-time early warning when the data anomaly exceeds the threshold of the preset indicator abnormal early warning threshold system; effectively realize the intelligent monitoring and early warning of fuel data, and ensure the standardized management of fuel intelligent monitoring.

[0014] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0015] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A schematic diagram of the structure of a fuel intelligent monitoring and early warning system provided in an embodiment of the present invention; Figure 2 The present invention provides a flowchart of a fuel intelligent monitoring and early warning method in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] like Figure 1 As shown, the embodiment of the present invention provides a fuel intelligent monitoring and early warning system, which mainly includes the following structures: Monitoring deployment module: used to determine the fuel monitoring sensor type and sensor deployment location according to the fuel monitoring indicators and perform corresponding sensor deployment; Data processing module: used to obtain fuel monitoring data based on deployed sensors and perform data processing, and transmit the processed fuel monitoring data to the fuel monitoring early warning platform; Analysis and early warning module: used to construct a fuel intelligent monitoring and early warning algorithm and a data mining model to analyze the data received by the fuel monitoring and early warning platform, determine data anomalies, and execute real-time early warning when the data anomaly exceeds the threshold of the preset indicator abnormal early warning threshold system.

[0020] In this embodiment, the fuel monitoring indicator refers to an indicator generated according to business requirements and meeting business requirements, such as a monitoring indicator of fuel supply.

[0021] In this embodiment, the fuel monitoring data refers to the fuel data obtained through sensor monitoring, such as the fuel supply amount in each time period.

[0022] In this embodiment, the fuel monitoring and early warning platform refers to a platform for receiving and processing fuel monitoring data and issuing corresponding real-time early warnings.

[0023] In this embodiment, the fuel intelligent monitoring and early warning algorithm refers to an algorithm for determining whether the fuel monitoring data is abnormal. For example, according to the fuel intelligent monitoring and early warning algorithm, the fuel monitoring data a1 is determined to be normal and no early warning is needed; the fuel monitoring data a2 is determined to be abnormal and a real-time early warning is issued.

[0024] In this embodiment, the data mining model refers to mining the mutual influence relationship between fuel monitoring data.

[0025] In this embodiment, the data abnormal value refers to the abnormal value of the fuel monitoring data. When the data abnormal value exceeds the threshold of the preset indicator abnormal warning threshold system, the data is determined to be abnormal and a real-time warning is issued.

[0026] In this embodiment, the preset indicator abnormal warning threshold system refers to a system constructed according to the fuel monitoring indicators, which is used to detect whether the fuel monitoring data is abnormal.

[0027] In this embodiment, the threshold of the preset indicator abnormal warning threshold system is used to distinguish and determine whether the fuel monitoring data is abnormal. When the data abnormality value of the fuel monitoring data exceeds the threshold of the preset indicator abnormal warning threshold system, the data is determined to be abnormal.

[0028] The beneficial effects of the above technical solution are: determining and deploying fuel monitoring sensors based on fuel monitoring indicators; acquiring fuel monitoring data for data processing and transmitting it to the fuel monitoring and early warning platform; constructing a fuel intelligent monitoring and early warning algorithm and a data mining model to perform data analysis on the received data of the fuel monitoring and early warning platform, determine data anomalies, and when the data anomalies exceed the threshold of the preset indicator abnormal warning threshold system, execute real-time warning; it not only effectively realizes the intelligent monitoring and early warning of fuel data, but also ensures the standardized management of fuel intelligent monitoring.

[0029] The embodiment of the present invention provides a fuel intelligent monitoring and early warning system, a monitoring deployment module, including: A fuel monitoring indicator unit, used to determine the fuel monitoring indicator according to the preset fuel monitoring target and historical fuel monitoring data; A sensor unit, used to determine the type of fuel monitoring sensor and the sensor deployment location according to the fuel monitoring index, and dynamically monitor and control the number of various sensors monitored according to historical fuel monitoring data; A monitoring and deployment unit, used to perform corresponding sensor deployment according to the sensor deployment position and the dynamic monitoring and control result; The deployed sensors are monitored and calibrated. When the monitoring output value of the sensor is consistent with the monitoring calibration value, it is determined that the deployment of the corresponding sensor is completed.

[0030] In this embodiment, fuel monitoring targets are preset, such as fuel supply quantity, fuel consumption quantity, fuel storage quantity, fuel quality and fuel combustion data.

[0031] In this embodiment, the type of sensor for fuel monitoring is determined, such as a temperature sensor or a pressure sensor.

[0032] In this embodiment, the sensor deployment position refers to a position that ensures the accuracy of monitoring data and has the least interference effect on the monitoring data.

[0033] In this embodiment, the number of sensors monitored by various types of sensors is dynamically monitored and controlled according to historical fuel monitoring data. For example, the fuel consumption in time period t1 is low, corresponding to the number of sensors a1; the fuel consumption in time period t2 is high, corresponding to the sensor data a2, a1 <a2。

[0034] In this embodiment, the deployed sensors are monitored and calibrated to ensure the accuracy of the monitoring data.

[0035] In this embodiment, the sensor is regularly maintained and calibrated.

[0036] The beneficial effect of the above technical solution is: by presetting the fuel monitoring target and historical fuel monitoring data, the fuel monitoring index is determined and then the sensor is deployed and the monitoring calibration is performed, which is conducive to ensuring the accuracy of the fuel monitoring data.

[0037] The embodiment of the present invention provides a fuel intelligent monitoring and early warning system, a fuel monitoring indicator unit, including: The fuel monitoring indicator analysis framework block is used to construct a fuel monitoring indicator analysis framework based on the preset fuel monitoring target; A fuel monitoring indicator block is used to obtain fuel supply, fuel consumption, fuel storage, fuel quality and fuel combustion data based on historical fuel monitoring data and generate corresponding initial fuel monitoring indicators; The initial fuel monitoring indicator is classified and processed according to the preset fuel monitoring target and analyzed and processed according to the fuel monitoring indicator analysis framework, and when it is monitored that the initial fuel monitoring indicator meets the fuel monitoring requirement, the corresponding initial fuel monitoring indicator is determined to be a fuel monitoring indicator; Otherwise, the corresponding indicators will be eliminated.

[0038] In this embodiment, a fuel monitoring indicator analysis framework is constructed based on preset fuel monitoring targets to optimize the analysis efficiency of fuel monitoring indicators, ensuring that each fuel monitoring indicator is based on fuel monitoring requirements and meets fuel monitoring requirements. For example, a fuel monitoring indicator analysis framework is constructed based on preset fuel monitoring targets a1, a2 and a3.

[0039] In this embodiment, the initial fuel monitoring index refers to a fuel monitoring index obtained based on historical fuel monitoring data.

[0040] The beneficial effects of the above technical solution are: building a fuel monitoring indicator analysis framework and performing indicator processing based on the corresponding initial fuel monitoring indicators generated according to historical fuel monitoring data, which is conducive to ensuring that each fuel monitoring indicator is based on business needs and meets business needs, thereby achieving standardized management and continuous operation of fuel monitoring indicators.

[0041] The embodiment of the present invention provides a fuel intelligent monitoring and early warning system, a data processing module, including: A data integration unit, used for integrating and processing the fuel monitoring data acquired by the sensor within the current cycle time period according to the data upload cycle; A data processing unit, used for preprocessing the fuel monitoring data and performing data conversion processing according to the data standard of the fuel monitoring early warning platform; When the data conversion process is completed, the data is compressed and stored; A data transmission unit, used to establish a stable connection between the data storage area and the fuel monitoring and early warning platform and to encrypt and transmit the processed fuel monitoring data to the fuel monitoring and early warning platform; When the data received by the fuel monitoring early warning platform is consistent with the fuel monitoring data after the data processing, it is determined that the data transmission is completed; Otherwise, retransmit the data.

[0042] In this embodiment, the fuel monitoring data acquired by the sensor in the current cycle time period is integrated and processed according to the data upload cycle. For example, in the data upload cycle t1, the fuel monitoring data in the upload cycle t1 time period is integrated.

[0043] In this embodiment, data integration refers to unified processing of fuel monitoring data.

[0044] In this embodiment, data preprocessing is performed on the fuel monitoring data, such as noise removal.

[0045] In this embodiment, the data standard of the fuel monitoring and early warning platform refers to the optimal analysis format of the fuel monitoring and early warning platform for analyzing fuel monitoring data. For example, the fuel monitoring and early warning platform determines that the optimal analysis format of fuel monitoring data a1 is b1, then the data standard of the fuel monitoring and early warning platform for fuel monitoring data a1 is b1.

[0046] The beneficial effects of the above technical solution are: integrating fuel monitoring data is conducive to the subsequent analysis of the relationship between fuel monitoring data to locate anomalies; performing data preprocessing, data conversion processing, data compression processing and data encryption transmission to ensure data validity, security and data processing efficiency.

[0047] The embodiment of the present invention provides a fuel intelligent monitoring and early warning system, an analysis and early warning module, including: A data mining model unit, used to obtain historical abnormal data based on historical fuel monitoring data, and select historical abnormal data that has data correlation with the fuel monitoring index to construct a historical abnormal data set; Reorder the historical abnormal data set according to the monitoring period to obtain the monitoring accuracy of the fuel monitoring indicator, and divide the reordered historical abnormal data set into historical abnormal data subsets of the monitoring accuracy value according to the monitoring accuracy value; Performing data mining on the historical abnormal data subset to obtain a feature vector of the historical abnormal data subset; Performing superposition statistics on the characteristic vectors of each historical abnormal data subset, determining the first data mining value of the historical abnormal data set, and constructing a data mining model; A data mining unit, configured to input the received data into a data mining model, determine a second data mining value of the received data, and when the second data mining value is not lower than the first data mining value, determine that the data mining model performs effective data mining on the received data; Otherwise, it is determined that the data mining model performs invalid data mining on the received data and performs sequential data mining on an indicator-by-indicator basis according to the fuel monitoring indicators; A fuel intelligent monitoring and early warning algorithm unit, used to construct a fuel intelligent monitoring and early warning algorithm based on the data mining model and historical fuel monitoring data; An early warning threshold unit, used to construct a preset indicator abnormal early warning threshold system according to the fuel monitoring indicator; Obtaining a threshold of a preset indicator abnormality warning threshold system, determining a threshold correlation between the received data and the threshold of the preset indicator abnormality warning threshold system according to historical fuel monitoring data, dynamically adjusting the threshold, and determining a dynamically adjusted threshold of the preset indicator abnormality threshold system; A fuel monitoring unit, configured to perform data analysis on the received data of the fuel monitoring and early warning platform according to the data mining model and the fuel intelligent monitoring and early warning algorithm, and determine data abnormal values ​​of the received data; ; Among them, F represents the data outlier of the received data; y1 represents the number of valid data mining in the received data; y2 represents the number of sequential data mining by indicator in the received data; Indicates the number of received data that have a threshold correlation with the j1th fuel monitoring indicator in the received data; represents the fuel monitoring value of the i1th received data in the j1th fuel monitoring indicator; Indicates the dynamic adjustment threshold of the j1th fuel monitoring indicator in the preset indicator abnormal threshold system; represents the threshold value of the j1th fuel monitoring indicator in the preset indicator abnormal threshold system; m1 represents the number of fuel monitoring indicators in the preset indicator abnormal threshold system; When the data abnormal value of the received data exceeds the dynamically adjusted threshold of the preset indicator abnormal warning threshold system, it is determined that there is abnormal received data in the received data and the abnormal received data is marked; An abnormal data impact unit, used for randomly selecting abnormal received data and other received data when it is determined that there is abnormal received data in the received data, and determining the data impact of the randomly selected abnormal received data on other received data according to the fuel intelligent monitoring and early warning algorithm; When the data influence degree of the randomly selected abnormal received data on other received data is not less than the preset influence degree, the randomly selected abnormal received data is determined to be the strong influence data corresponding to the other received data, and a strong influence label is added; Otherwise, determining that the randomly selected abnormal received data is weakly affected data corresponding to the other received data, and adding a weakly affected label; When there is no data influence between the randomly selected abnormal received data and other received data, the randomly selected abnormal received data and the corresponding other received data are determined to be non-influenced data, and a non-influence label is added; The receiving data relation unit is used to segment the fuel combustion process, and divide the receiving data corresponding to the monitoring data of the fuel unburned section into a first type of receiving data, and divide the receiving data corresponding to the monitoring data of the fuel burning section into a second type of receiving data; Determine the mutual influence relationship between the first type of received data and the second type of received data according to the data mining model; An abnormality locating unit, configured to locate abnormal origin data of the abnormal reception data according to the influence label and the mutual influence relationship in combination with the abnormal reception data; The real-time warning unit is used to call corresponding alarm data from the alarm database for real-time warning according to the abnormal origin data.

[0048] In this embodiment, data correlation refers to the influence relationship between the fuel monitoring data and the fuel monitoring index.

[0049] In this embodiment, the historical abnormal data set refers to a set of historical abnormal data that has data correlation with the fuel monitoring indicator, which is used for constructing a subsequent data mining model. For example, a historical abnormal data set (b1, b2) is constructed based on historical abnormal data b1 and historical abnormal data b2 that have data correlation with the fuel monitoring indicator a1.

[0050] In this embodiment, the higher the monitoring accuracy of the fuel monitoring index, the higher the monitoring accuracy of the fuel monitoring data.

[0051] In this embodiment, reordering the historical abnormal data set according to the monitoring accuracy value and dividing it into historical abnormal data subsets of the monitoring accuracy value means dividing the time periods equally. For example, if the monitoring accuracy of the fuel monitoring indicator a2 is 5 (1-10), then the historical abnormal data set corresponding to the fuel monitoring indicator a2 is divided into 5 historical abnormal data subsets. The monitoring time period of the fuel monitoring indicator is t1, and the fuel monitoring data corresponding to each t1 / 5 monitoring time period is a historical abnormal data subset.

[0052] In this embodiment, the data mining process refers to determining data correlations between data.

[0053] In this embodiment, the first data mining value refers to a quantitative value of the data mining processing capability of the data mining model on the data. The higher the first data mining value is, the better the data mining processing of the data by the data mining model is.

[0054] In this embodiment, the second data mining value refers to a quantitative value of the data mining processing capability of the data mining model on the received data.

[0055] In this embodiment, effective data mining means that the data mining model successfully determines the data correlation between the received data and other received data.

[0056] In this embodiment, invalid data mining means that the data mining model cannot successfully determine the data correlation between the received data and other received data.

[0057] In this embodiment, sequential data mining by indicators refers to narrowing the scope of data correlation analysis according to the fuel monitoring indicators, thereby increasing the possibility of determining the data correlation between the received data and other received data, thereby achieving effective data mining.

[0058] In this embodiment, the threshold correlation between the received data and the threshold of the preset indicator abnormal warning threshold system refers to dynamically adjusting the threshold of the preset indicator abnormal warning threshold system according to the received data, thereby ensuring that the threshold of the preset indicator abnormal warning threshold system meets the fuel monitoring requirements.

[0059] In this embodiment, the threshold is dynamically adjusted based on the threshold correlation between the received data and the threshold of the preset indicator abnormal warning threshold system determined according to the historical fuel monitoring data. For example, based on the historical fuel monitoring data b3, the threshold of the preset indicator abnormal warning threshold system for the historical fuel monitoring data b3 is e3, and the time period t1 is dynamically adjusted to e4 based on the threshold correlation.

[0060] In this embodiment, a dynamically adjusted threshold value of a preset indicator abnormal threshold value system is determined. For example, the threshold value e3 of the historical fuel monitoring data b3 is dynamically adjusted to the dynamically adjusted threshold value e4 during the time period t1.

[0061] In this embodiment, the data influence degree of the randomly selected abnormal received data on other received data refers to the influence degree determined according to the data correlation between the data; the higher the data correlation, the higher the corresponding data influence degree.

[0062] In this embodiment, when a strong influence label is added, it is determined that the other received data is greatly influenced by the randomly selected abnormal received data, and the other received data is determined to be abnormal received data.

[0063] In this embodiment, when a weak impact label is added, it is determined that the other received data is less affected by the randomly selected abnormal received data, and a subsequent determination is required as to whether the other received data is abnormal received data.

[0064] In this embodiment, when the no-impact label is added, it is determined that the other received data is not affected by the randomly selected abnormal received data, and the other received data is determined to be normal received data.

[0065] In this embodiment, one type of received data includes, for example, fuel supply quantity, fuel consumption quantity, fuel storage quantity, and fuel quality; and the second type of received data includes, for example, fuel combustion data.

[0066] In this embodiment, the mutual influence relationship between the first category received data and the second category received data is determined based on the data mining model. For example, when there is an abnormality in the first category received data, it is determined that there must be an abnormality in the second category received data; when there is an abnormality in the second category received data, it is determined that there may be an abnormality in the first category received data.

[0067] In this embodiment, the abnormal origin data refers to the initial fuel monitoring data where the abnormality occurs. For example, the abnormal received data b4 is in the time period t1, and the positioning corresponding abnormal origin data is the received data b5 in the time period t2.

[0068] The beneficial effects of the above technical solution are: by constructing a fuel intelligent monitoring and early warning algorithm and a data mining model, it is conducive to data analysis of fuel monitoring data, revealing insights into fuel supply demand and storage relationships; determining data outliers and executing real-time early warnings, effectively locating data anomalies, and facilitating the subsequent implementation of corresponding abnormal control strategies.

[0069] The embodiment of the present invention provides a fuel intelligent monitoring and early warning system, a real-time early warning unit, including: An exception analysis block is used to analyze the exception origin data and determine the exception type of the exception origin data; The abnormal warning block is used to call the corresponding abnormal type alarm database according to the abnormal type and perform abnormal matching. When the abnormal matching is successful, the corresponding alarm data is called for real-time warning and the abnormal alarm data is recorded; Otherwise, new alarm data is generated for real-time warning and the alarm data is stored.

[0070] In this embodiment, the abnormal origin data is parsed to determine the abnormal type of the abnormal origin data. For example, it is determined that the abnormal type of the abnormal origin data is a fuel supply abnormality.

[0071] In this embodiment, all monitoring data and call alarm data are recorded and stored according to time periods, which is convenient for subsequent fuel monitoring management and early warning.

[0072] The beneficial effects of the above technical solution are: by analyzing the abnormal origin data, it is helpful to specifically determine the abnormal type and lay a data foundation for subsequent early warning; calling the corresponding abnormal type alarm database and performing abnormal matching improves the fuel early warning efficiency and is conducive to achieving real-time early warning.

[0073] The embodiment of the present invention provides a fuel intelligent monitoring and early warning system, further comprising: A visualization module, for visually displaying fuel monitoring indicators, the received data, abnormal origin data and alarm data; The prediction and warning module is used to predict the supply, consumption and storage of fuel based on the current period fuel monitoring data and historical fuel monitoring data, and to perform prediction and warning in combination with the indicator abnormal warning threshold system.

[0074] In this embodiment, the fuel monitoring index, the received data, the abnormal origin data and the alarm data are uniformly visualized and displayed. For example, the fuel monitoring index a1, the corresponding received data b1, the abnormal origin data c1 and the alarm data d1 are uniformly visualized and displayed under the fuel monitoring index a1, and the abnormal origin data c1 and the alarm data d1 are color-coded, such as marked in red, for easy observation.

[0075] In this embodiment, prediction and warning are performed. For example, if the fuel monitoring data a1 is monitored normally in the current time period, and it is predicted that the fuel monitoring data may be abnormal in the next time period t1, a prediction and warning is performed, and the fuel monitoring data is color-coded, such as marked in blue.

[0076] In this embodiment, the fuel is monitored and managed according to the prediction and warning results.

[0077] The beneficial effect of the above technical solution is: through visual processing and prediction of fuel monitoring data, it is conducive to timely discovery and processing of abnormal fuel data, avoiding the occurrence of business failures, and ensuring fuel management safety and stable operation management.

[0078] like Figure 2As shown, the embodiment of the present invention provides a fuel intelligent monitoring and early warning method, which mainly includes the following steps: Step 1: Determine the type of fuel monitoring sensor and the sensor deployment location based on the fuel monitoring indicators and deploy the corresponding sensors; Step 2: Obtain fuel monitoring data from the deployed sensors and process the data, and transmit the processed fuel monitoring data to the fuel monitoring early warning platform; Step 3: Construct a fuel intelligent monitoring and early warning algorithm and a data mining model to perform data analysis on the received data of the fuel monitoring and early warning platform, determine data anomalies, and execute real-time warning when the data anomaly exceeds the threshold of the preset indicator abnormal warning threshold system.

[0079] The beneficial effects of the above technical solution are: determining and deploying fuel monitoring sensors based on fuel monitoring indicators; acquiring fuel monitoring data for data processing and transmitting it to the fuel monitoring and early warning platform; constructing a fuel intelligent monitoring and early warning algorithm and a data mining model to perform data analysis on the received data of the fuel monitoring and early warning platform, determine data anomalies, and when the data anomalies exceed the threshold of the preset indicator abnormal warning threshold system, execute real-time warning; it not only effectively realizes the intelligent monitoring and early warning of fuel data, but also ensures the standardized management of fuel intelligent monitoring.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fuel intelligent monitoring and early warning system, characterized in that: include: Monitoring deployment module: used to determine the fuel monitoring sensor type and sensor deployment location according to the fuel monitoring indicators and perform corresponding sensor deployment; Data processing module: used to obtain fuel monitoring data based on deployed sensors and perform data processing, and transmit the processed fuel monitoring data to the fuel monitoring early warning platform; Analysis and early warning module: used to construct a fuel intelligent monitoring and early warning algorithm and a data mining model to analyze the data received by the fuel monitoring and early warning platform, determine data anomalies, and execute real-time early warning when the data anomaly exceeds the threshold of the preset indicator abnormal early warning threshold system.

2. The intelligent fuel monitoring and early warning system according to claim 1 is characterized in that: Monitoring deployment modules, including: A fuel monitoring indicator unit, used to determine the fuel monitoring indicator according to the preset fuel monitoring target and historical fuel monitoring data; A sensor unit, used to determine the type of fuel monitoring sensor and the sensor deployment location according to the fuel monitoring index, and dynamically monitor and control the number of various sensors monitored according to historical fuel monitoring data; A monitoring and deployment unit, used to perform corresponding sensor deployment according to the sensor deployment position and the dynamic monitoring and control result; The deployed sensors are monitored and calibrated. When the monitoring output value of the sensor is consistent with the monitoring calibration value, it is determined that the deployment of the corresponding sensor is completed.

3. A fuel intelligent monitoring and early warning system according to claim 2, characterized in that: Fuel monitoring indicator unit, including: The fuel monitoring indicator analysis framework block is used to construct a fuel monitoring indicator analysis framework based on the preset fuel monitoring target; A fuel monitoring indicator block is used to obtain fuel supply, fuel consumption, fuel storage, fuel quality and fuel combustion data based on historical fuel monitoring data and generate corresponding initial fuel monitoring indicators; The initial fuel monitoring indicator is classified and processed according to the preset fuel monitoring target and analyzed and processed according to the fuel monitoring indicator analysis framework, and when it is monitored that the initial fuel monitoring indicator meets the fuel monitoring requirement, the corresponding initial fuel monitoring indicator is determined to be a fuel monitoring indicator; Otherwise, the corresponding indicators will be eliminated.

4. The intelligent fuel monitoring and early warning system according to claim 1 is characterized in that: Data processing module, including: A data integration unit, used for integrating and processing the fuel monitoring data acquired by the sensor within the current cycle time period according to the data upload cycle; A data processing unit, used for preprocessing the fuel monitoring data and performing data conversion processing according to the data standard of the fuel monitoring early warning platform; When the data conversion process is completed, the data is compressed and stored; A data transmission unit, used to establish a stable connection between the data storage area and the fuel monitoring and early warning platform and to encrypt and transmit the processed fuel monitoring data to the fuel monitoring and early warning platform; When the data received by the fuel monitoring early warning platform is consistent with the fuel monitoring data after the data processing, it is determined that the data transmission is completed; Otherwise, retransmit the data.

5. The intelligent fuel monitoring and early warning system according to claim 1 is characterized in that: Analysis and early warning module, including: A data mining model unit, used to obtain historical abnormal data based on historical fuel monitoring data, and select historical abnormal data that has data correlation with the fuel monitoring index to construct a historical abnormal data set; Reorder the historical abnormal data set according to the monitoring period to obtain the monitoring accuracy of the fuel monitoring indicator, and divide the reordered historical abnormal data set into historical abnormal data subsets of the monitoring accuracy value according to the monitoring accuracy value; Performing data mining on the historical abnormal data subset to obtain a feature vector of the historical abnormal data subset; Performing superposition statistics on the characteristic vectors of each historical abnormal data subset, determining the first data mining value of the historical abnormal data set, and constructing a data mining model; A data mining unit, configured to input the received data into a data mining model, determine a second data mining value of the received data, and when the second data mining value is not lower than the first data mining value, determine that the data mining model performs effective data mining on the received data; Otherwise, it is determined that the data mining model performs invalid data mining on the received data and performs sequential data mining on an indicator-by-indicator basis according to the fuel monitoring indicators; A fuel intelligent monitoring and early warning algorithm unit, used to construct a fuel intelligent monitoring and early warning algorithm based on the data mining model and historical fuel monitoring data; An early warning threshold unit, used to construct a preset indicator abnormal early warning threshold system according to the fuel monitoring indicator; Obtaining a threshold of a preset indicator abnormality warning threshold system, determining a threshold correlation between the received data and the threshold of the preset indicator abnormality warning threshold system according to historical fuel monitoring data, dynamically adjusting the threshold, and determining a dynamically adjusted threshold of the preset indicator abnormality threshold system; A fuel monitoring unit, configured to perform data analysis on the received data of the fuel monitoring and early warning platform according to the data mining model and the fuel intelligent monitoring and early warning algorithm, and determine data abnormal values ​​of the received data; ； Among them, F represents the data outlier of the received data; y1 represents the number of valid data mining in the received data; y2 represents the number of sequential data mining by indicator in the received data; Indicates the number of received data that have a threshold correlation with the j1th fuel monitoring indicator in the received data; represents the fuel monitoring value of the i1th received data in the j1th fuel monitoring indicator; Indicates the dynamic adjustment threshold of the j1th fuel monitoring indicator in the preset indicator abnormal threshold system; represents the threshold value of the j1th fuel monitoring indicator in the preset indicator abnormal threshold system; m1 represents the number of fuel monitoring indicators in the preset indicator abnormal threshold system; When the data abnormal value of the received data exceeds the dynamically adjusted threshold of the preset indicator abnormal warning threshold system, it is determined that there is abnormal received data in the received data and the abnormal received data is marked; An abnormal data impact unit, used for randomly selecting abnormal received data and other received data when it is determined that there is abnormal received data in the received data, and determining the data impact of the randomly selected abnormal received data on other received data according to the fuel intelligent monitoring and early warning algorithm; When the data influence degree of the randomly selected abnormal received data on other received data is not less than the preset influence degree, the randomly selected abnormal received data is determined to be the strong influence data corresponding to the other received data, and a strong influence label is added; Otherwise, determining that the randomly selected abnormal received data is weakly affected data corresponding to the other received data, and adding a weakly affected label; When there is no data influence between the randomly selected abnormal received data and other received data, the randomly selected abnormal received data and the corresponding other received data are determined to be non-influenced data, and a non-influence label is added; The receiving data relation unit is used to segment the fuel combustion process, and divide the receiving data corresponding to the monitoring data of the fuel unburned section into a first type of receiving data, and divide the receiving data corresponding to the monitoring data of the fuel burning section into a second type of receiving data; Determine the mutual influence relationship between the first type of received data and the second type of received data according to the data mining model; An abnormality locating unit, configured to locate abnormal origin data of the abnormal reception data according to the influence label and the mutual influence relationship in combination with the abnormal reception data; The real-time warning unit is used to call corresponding alarm data from the alarm database for real-time warning according to the abnormal origin data.

6. The intelligent fuel monitoring and early warning system according to claim 5 is characterized in that: Real-time warning unit, including: An exception analysis block is used to analyze the exception origin data and determine the exception type of the exception origin data; The abnormal warning block is used to call the corresponding abnormal type alarm database according to the abnormal type and perform abnormal matching. When the abnormal matching is successful, the corresponding alarm data is called for real-time warning and the abnormal alarm data is recorded; Otherwise, new alarm data is generated for real-time warning and the alarm data is stored.

7. The intelligent fuel monitoring and early warning system according to claim 1 is characterized in that: Also includes: A visualization module, for visually displaying fuel monitoring indicators, the received data, abnormal origin data and alarm data; The prediction and warning module is used to predict the supply, consumption and storage of fuel based on the current period fuel monitoring data and historical fuel monitoring data, and to perform prediction and warning in combination with the indicator abnormal warning threshold system.

8. A fuel intelligent monitoring and early warning method, characterized in that: include: Step 1: Determine the type of fuel monitoring sensor and the sensor deployment location based on the fuel monitoring indicators and deploy the corresponding sensors; Step 2: Obtain fuel monitoring data from the deployed sensors and process the data, and transmit the processed fuel monitoring data to the fuel monitoring early warning platform; Step 3: Construct a fuel intelligent monitoring and early warning algorithm and a data mining model to perform data analysis on the received data of the fuel monitoring and early warning platform, determine data anomalies, and execute real-time warning when the data anomaly exceeds the threshold of the preset indicator abnormal warning threshold system.

Images