Power plant coal inventory intelligent early warning system and method

Abstract

The invention provides a power plant coal inventory intelligent early warning system and method, and relates to the technical field of intelligent early warning, and the system comprises the steps: obtaining and preprocessing power plant coal inventory data and power plant coal inventory influence data in real time, and integrating and extracting data features; constructing and training a power plant coal inventory prediction model according to historical power plant coal inventory data in combination with the time sequence, inputting the data features, and generating power plant coal inventory prediction data; setting early warning logic, acquiring power plant coal scheduling data, performing early warning correction on the power plant coal inventory prediction data, and generating intelligent early warning data when it is judged that the early warning corrected power plant coal inventory prediction data is matched with the early warning logic; and high-efficiency and high-quality intelligent early warning of the coal inventory of the power plant is realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent early warning technology, and in particular to an intelligent early warning system and method for coal inventory in a power plant. Background Art

[0002] As the scale of power plants continues to expand, the in-and-out situation of coal resources in power plants has become increasingly complicated. If the coal inventory of power plants is insufficient, it will seriously affect the normal and stable operation of the power plants. Traditional power plant coal inventory warnings are mainly based on statistical data on the in-and-out of coal in power plants. The warnings are delayed and easily affected by many factors such as the implementation of the in-and-out of coal resources in power plants, transportation in transit, and consumption. The warning efficiency and quality are low.

[0003] Therefore, the present invention provides an intelligent early warning system and method for coal inventory in a power plant. Summary of the invention

[0004] The present invention provides an intelligent early warning system and method for coal inventory in a power plant. The system acquires and preprocesses coal inventory data and data affecting coal inventory in a power plant in real time, integrates and extracts data features; constructs and trains a coal inventory prediction model for a power plant based on historical coal inventory data of the power plant in combination with a time series, inputs the data features, and generates coal inventory prediction data for the power plant; sets early warning logic, acquires coal dispatching data of the power plant, performs early warning correction on the coal inventory prediction data of the power plant, and generates intelligent early warning data when it is determined that the coal inventory prediction data of the power plant after early warning correction matches the early warning logic; and realizes efficient and high-quality intelligent early warning of coal inventory in the power plant.

[0005] The present invention provides an intelligent early warning system for coal inventory in a power plant, comprising: A data acquisition module is used to acquire and pre-process the power plant coal inventory data and the power plant coal inventory impact data in real time, integrate the power plant coal inventory data and the power plant coal inventory impact data acquired in real time and extract data features; A data prediction module is used to construct and train a power plant coal inventory prediction model based on historical power plant coal inventory data combined with time series, input the data features, and generate power plant coal inventory prediction data; The intelligent early warning module is used to set the early warning logic, obtain the coal dispatching data of the power plant, and perform early warning correction on the coal inventory forecast data of the power plant. When it is determined that the early warning corrected coal inventory forecast data of the power plant matches the early warning logic, the intelligent early warning data is generated.

[0006] According to the present invention, a power plant coal inventory intelligent early warning system, a data acquisition module, includes: A data acquisition unit is used to acquire the power plant coal inventory data and the power plant coal inventory impact data in real time, wherein the power plant coal inventory impact data includes: resource implementation data, in-transit transportation data, cycle consumption data and weather change data; A data preprocessing unit is used to clean and convert the real-time coal inventory data and coal in-and-out data of power plants; The data integration unit is used to set data integration categories and classify and integrate the data cleaning and data conversion results, wherein the data integration categories include: power plant coal inventory data category, power plant coal incoming data category, and power plant coal outgoing data category; The data feature extraction unit is used to determine the current warning scenario of the power plant's coal inventory data based on the data integration result, and then extract the data features.

[0007] According to the present invention, a power plant coal inventory intelligent early warning system, a data feature extraction unit includes: The early warning scenario block is used to obtain the power plant's coal inventory data and the power plant's coal inventory impact data for a second time based on the data integration results, and to determine the current early warning scenario of the power plant's coal inventory data based on historical early warning scenarios. The historical early warning scenarios include: the power plant's imported coal delay early warning scenario, the power plant's domestic trade coal to loading port delay early warning scenario, the power plant's domestic trade coal to loading port excessively long early warning scenario, the power plant's domestic trade coal to unloading port delay early warning scenario and the power plant's coal inventory early warning scenario.

[0008] According to the present invention, a power plant coal inventory intelligent early warning system, a data prediction module, includes: A model building unit is used to select a learning model, build a power plant coal inventory prediction model based on historical power plant coal inventory data combined with time series, and perform data prediction on the power plant coal inventory; A training and verification unit, used to randomly select historical power plant coal inventory data, divide it into a training set, a verification set and a test set, and train the power plant coal inventory prediction model and verify the prediction performance; The model testing unit is used to perform a model test on the power plant coal inventory prediction model that has been trained and verified, input the test data into the power plant coal inventory prediction model that has been trained and verified, and if the output result is consistent with the preset test result, the model test is determined to be qualified; The forecasting data unit is used to input data features into the power plant coal inventory forecasting model that has passed the model test to generate the power plant coal inventory forecasting data.

[0009] According to the present invention, a power plant coal inventory intelligent early warning system and an intelligent early warning module include: An early warning logic setting unit is used to divide the coal inventory data of the power plant according to the coal inventory time and the coal inventory type of the power plant, and set the early warning logic of the coal inventory of the power plant; Set an early warning cycle and a power plant coal inventory safety cycle, and calculate the coal inventory data of the power plant in each sub-alert cycle within the early warning cycle according to the early warning logic of the power plant coal inventory; Obtain the amount of coal that has been unloaded but not put into inventory, the amount of incoming coal, and the daily consumption in the current sub-warning cycle, and combine the coal inventory data of the previous power plant in the previous warning cycle of the current sub-warning cycle to determine the current power plant coal inventory data of the current sub-warning cycle; Obtain the total power plant coal inventory data of the early warning period. If the current power plant coal inventory data of the current sub-early warning period is within the total power plant coal inventory data of the early warning ratio, generate the power plant coal inventory early warning data; If the current power plant coal inventory data of the current sub-warning cycle is within the total power plant coal inventory data of the alarm ratio, the power plant coal inventory primary alarm data is generated; An early warning correction unit is used to obtain the data ratio of the actual data of the power plant's coal inventory in the previous sub-early warning cycle to the predicted data of the power plant's coal inventory in the previous sub-early warning cycle when monitoring the primary early warning data of the power plant's coal inventory or the primary alarm data of the power plant's coal inventory, and record it as the early warning correction ratio of the power plant's coal inventory predicted data in the current sub-early warning cycle; Obtain the power plant coal dispatching data, and perform periodic warning correction on the power plant coal inventory forecast data of the current sub-warning cycle in combination with the sub-warning cycle. The power plant coal dispatching data includes: dispatching data on the amount of coal unloaded but not in stock, dispatching data on incoming coal, and dispatching data on daily consumption; An intelligent early warning unit, used to calculate the secondary power plant coal inventory data in each sub-early warning period within the early warning period according to the power plant coal inventory early warning logic combined with the early warning correction result; ;in, Indicates the first Coal inventory data of secondary power plants within each sub-warning period; Indicates Actual data of coal inventory of power plants in the previous sub-warning cycle; Indicates Coal supply dispatching data within a warning cycle; Indicates Daily consumption dispatch data within each sub-warning cycle; Indicates Dispatching data of coal quantity unloaded but not stored in stock within each sub-warning cycle; Indicates Actual data of coal inventory of power plants in each sub-warning cycle; Indicates Coal inventory forecast data for power plants for each sub-warning cycle; Indicates Input of data features of each sub-warning cycle; represents the weight matrix of the power plant coal inventory forecasting model; Indicates bias; represents the activation function; Indicates New coal dispatching data within a warning cycle; Indicates the total number of sub-warning cycles; When the secondary power plant coal inventory data is within the total power plant coal inventory data of the early warning ratio, generating power plant coal inventory secondary early warning data; The alarm unit is used to generate secondary alarm data of coal inventory in the power plant when the secondary power plant coal inventory data is within the alarm ratio of the total power plant coal inventory data.

[0010] According to the present invention, a power plant coal inventory intelligent early warning system further includes: Early warning alarm visualization unit, used to build a user visualization interface to display the early warning data of power plant coal inventory or the alarm data of power plant coal inventory in real time; The early warning alarm notification unit is used to generate notification data according to the power plant coal inventory early warning data or the power plant coal inventory alarm data, and send the notification data to relevant administrators according to the preset early warning alarm notification strategy.

[0011] According to the present invention, a power plant coal inventory intelligent early warning system further includes: The early warning elimination module is used to execute the preset early warning alarm elimination strategy when monitoring the power plant coal inventory early warning data or the power plant coal inventory alarm data, and generate and explain the actual elimination strategy.

[0012] The present invention provides an intelligent early warning method for coal inventory in a power plant, comprising: Step 1: Acquire and pre-process the power plant coal inventory data and the power plant coal inventory impact data in real time, integrate the power plant coal inventory data and the power plant coal inventory impact data acquired in real time and extract data features; Step 2: construct and train a power plant coal inventory forecasting model based on historical power plant coal inventory data combined with time series, input the data features, and generate power plant coal inventory forecasting data; Step 3: Set the early warning logic, obtain the power plant coal dispatching data, and perform early warning correction on the power plant coal inventory forecast data. When it is determined that the early warning corrected power plant coal inventory forecast data matches the early warning logic, generate intelligent early warning data.

[0013] Compared with the prior art, the present invention has the following beneficial effects: By acquiring and preprocessing the power plant coal inventory data and the power plant coal inventory impact data in real time, integrating and extracting data features; constructing and training the power plant coal inventory prediction model based on the historical power plant coal inventory data combined with the time series, inputting the data features, and generating the power plant coal inventory prediction data; setting the early warning logic, acquiring the power plant coal dispatching data, and performing early warning correction on the power plant coal inventory prediction data; when it is determined that the early warning corrected power plant coal inventory prediction data matches the early warning logic, generating intelligent early warning data; achieving efficient and high-quality intelligent early warning of the power plant coal inventory.

[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] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a structural schematic diagram of an intelligent early warning system for coal inventory in a power plant provided by an embodiment of the present invention; Figure 2 It is a flow chart of an intelligent early warning method for coal inventory in a power plant provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0018] Embodiment 1: The embodiment of the present invention provides an intelligent early warning system for coal inventory in a power plant, such as Figure 1 As shown, including: A data acquisition module is used to acquire and pre-process the power plant coal inventory data and the power plant coal inventory impact data in real time, integrate the power plant coal inventory data and the power plant coal inventory impact data acquired in real time and extract data features; A data prediction module is used to construct and train a power plant coal inventory prediction model based on historical power plant coal inventory data combined with time series, input the data features, and generate power plant coal inventory prediction data; The intelligent early warning module is used to set the early warning logic, obtain the coal dispatching data of the power plant, and perform early warning correction on the coal inventory forecast data of the power plant. When it is determined that the early warning corrected coal inventory forecast data of the power plant matches the early warning logic, the intelligent early warning data is generated.

[0019] In this embodiment, the power plant coal inventory impact data, that is, data that affects the power plant coal inventory data, such as resource implementation data, in-transit transportation data, cycle consumption data and weather change data.

[0020] In this embodiment, resource implementation data, i.e., actual inventory data; in-transit transportation data, i.e., data on coal to be stored; periodic consumption data, i.e., periodic consumption inventory data, for example, daily coal consumption data; and weather change data, i.e., different coal consumption data under different weather conditions.

[0021] In this embodiment, integrating and extracting data features refers to extracting features that have a significant impact on changes in coal inventory at a power plant, such as coal type, transportation method, and transportation distance.

[0022] In this embodiment, the power plant coal inventory prediction model is used to predict the coal consumption of the power plant coal inventory within the early warning period, for example, predicting the power plant coal inventory situation on each day in the next 15 days.

[0023] In this embodiment, the power plant coal inventory prediction data, for example, predicts the power plant coal inventory situation on each day within the next 15 days, wherein the power plant coal inventory situation prediction result on each day is the power plant coal inventory prediction data.

[0024] In this embodiment, the early warning logic refers to the logic of executing early warning according to the coal inventory of the power plant. For example, when the coal inventory of the power plant in time period a1 is lower than b1, an early warning is generated.

[0025] In this embodiment, the power plant coal dispatching data refers to the power plant coal in-and-out storage or consumption data, such as the dispatching data of the amount of coal that has not been stored in the storage, the dispatching data of the amount of incoming coal, and the dispatching data of the daily consumption.

[0026] In this embodiment, performing early warning correction on the power plant coal inventory forecast data refers to performing correction processing on the power plant coal inventory forecast data according to the power plant coal dispatching data to reduce the forecast error.

[0027] In this embodiment, the intelligent early warning data includes early warning data and alarm data, which are used to remind the corresponding administrator to replenish coal when the coal inventory of the power plant is insufficient to ensure the stable operation of the power plant.

[0028] The working principle and beneficial effects of the above technical solution are: by real-time acquisition and preprocessing of power plant coal inventory data and power plant coal inventory impact data, integrating and extracting data features; constructing and training a power plant coal inventory prediction model based on historical power plant coal inventory data combined with time series, inputting the data features, and generating power plant coal inventory prediction data; setting early warning logic, acquiring power plant coal scheduling data, and performing early warning correction on power plant coal inventory prediction data, and generating intelligent early warning data when it is determined that the early warning corrected power plant coal inventory prediction data matches the early warning logic; achieving efficient and high-quality intelligent early warning of power plant coal inventory.

[0029] Embodiment 2: The embodiment of the present invention provides a power plant coal inventory intelligent early warning system, a data acquisition module, including: A data acquisition unit is used to acquire the power plant coal inventory data and the power plant coal inventory impact data in real time, wherein the power plant coal inventory impact data includes: resource implementation data, in-transit transportation data, cycle consumption data and weather change data; A data preprocessing unit is used to clean and convert the real-time coal inventory data and coal in-and-out data of power plants; The data integration unit is used to set data integration categories and classify and integrate the data cleaning and data conversion results, wherein the data integration categories include: power plant coal inventory data category, power plant coal incoming data category, and power plant coal outgoing data category; The data feature extraction unit is used to determine the current warning scenario of the power plant's coal inventory data based on the data integration result, and then extract the data features.

[0030] In this embodiment, resources implement data, for example, data such as coal purchase contracts, arrival notices, and transportation plans of power plants are collected.

[0031] In this embodiment, the in-transit transportation data, for example, obtains information such as the real-time location, estimated arrival time, and transportation volume of coal transportation.

[0032] In this embodiment, periodic consumption data, for example, analyzes historical coal consumption data, and combines the periodic forecast and analysis of future coal consumption with power plant load changes, equipment operating status, etc.

[0033] In this embodiment, weather change data, for example, obtains weather forecast information, including temperature, humidity, wind speed, etc. Weather change data affects the transportation and consumption of coal and further affects the coal inventory data of power plants.

[0034] In this embodiment, data cleaning is performed, for example, to remove abnormal data and missing data.

[0035] In this embodiment, data conversion, for example, converts weather change data into corresponding weather quantitative score values.

[0036] In this embodiment, the early warning scenario is used to analyze the impact data of coal inventory in power plants.

[0037] The working principle and beneficial effects of the above technical solution are: by acquiring and preprocessing the power plant coal inventory data and the power plant coal inventory impact data in real time, integrating and extracting data features, a data foundation is laid for the subsequent intelligent early warning of power plant coal inventory.

[0038] Embodiment 3: The embodiment of the present invention provides a power plant coal inventory intelligent early warning system, a data feature extraction unit, including: The early warning scenario block is used to obtain the power plant's coal inventory data and the power plant's coal inventory impact data for a second time based on the data integration results, and to determine the current early warning scenario of the power plant's coal inventory data based on historical early warning scenarios. The historical early warning scenarios include: the power plant's imported coal delay early warning scenario, the power plant's domestic trade coal to loading port delay early warning scenario, the power plant's domestic trade coal to loading port excessively long early warning scenario, the power plant's domestic trade coal to unloading port delay early warning scenario and the power plant's coal inventory early warning scenario.

[0039] In this embodiment, the warning scenario is a scenario that may lead to a coal inventory warning for a power plant.

[0040] In this embodiment, the current warning scenario may include multiple warning scenarios. For example, the current warning scenario a1 includes: a warning scenario of a delay in imported coal for a power plant and a warning scenario of a delay in the arrival of domestic trade coal at a loading port for a power plant.

[0041] The working principle and beneficial effects of the above technical solution are: by secondary acquiring the power plant's coal inventory data and the power plant's coal inventory impact data based on the data integration results, and determining the current warning scenario of the power plant's coal inventory data based on historical warning scenarios, it is beneficial to improve the efficiency of data feature extraction, and thereby improve the efficiency of subsequent intelligent warning of power plant coal inventory.

[0042] Embodiment 4: The embodiment of the present invention provides a power plant coal inventory intelligent early warning system, a data prediction module, including: A model building unit is used to select a learning model, build a power plant coal inventory prediction model based on historical power plant coal inventory data combined with time series, and perform data prediction on the power plant coal inventory; A training and verification unit, used to randomly select historical power plant coal inventory data, divide it into a training set, a verification set and a test set, and train the power plant coal inventory prediction model and verify the prediction performance; The model testing unit is used to perform a model test on the power plant coal inventory prediction model that has been trained and verified, input the test data into the power plant coal inventory prediction model that has been trained and verified, and if the output result is consistent with the preset test result, the model test is determined to be qualified; The forecasting data unit is used to input data features into the power plant coal inventory forecasting model that has passed the model test to generate the power plant coal inventory forecasting data.

[0043] In this embodiment, a learning model is selected, such as a machine learning model or a convolutional neural network model.

[0044] In this embodiment, the power plant coal inventory forecast data, for example, forecasts the power plant coal inventory data for the next 15 days.

[0045] The working principle and beneficial effects of the above technical solution are: constructing and training a power plant coal inventory prediction model based on historical power plant coal inventory data combined with time series, inputting the data features, generating power plant coal inventory prediction data, and improving the quality of subsequent power plant coal inventory intelligent early warning.

[0046] Embodiment 5: The embodiment of the present invention provides a power plant coal inventory intelligent early warning system, an intelligent early warning module, including: An early warning logic setting unit is used to divide the coal inventory data of the power plant according to the coal inventory time and the coal inventory type of the power plant, and set the early warning logic of the coal inventory of the power plant; Set an early warning cycle and a power plant coal inventory safety cycle, and calculate the coal inventory data of the power plant in each sub-alert cycle within the early warning cycle according to the early warning logic of the power plant coal inventory; Obtain the amount of coal that has been unloaded but not put into inventory, the amount of incoming coal, and the daily consumption in the current sub-warning cycle, and combine the coal inventory data of the previous power plant in the previous warning cycle of the current sub-warning cycle to determine the current power plant coal inventory data of the current sub-warning cycle; Obtain the total power plant coal inventory data of the early warning period. If the current power plant coal inventory data of the current sub-early warning period is within the total power plant coal inventory data of the early warning ratio, generate the power plant coal inventory early warning data; If the current power plant coal inventory data of the current sub-warning cycle is within the total power plant coal inventory data of the alarm ratio, the power plant coal inventory primary alarm data is generated; An early warning correction unit is used to obtain the data ratio of the actual data of the power plant's coal inventory in the previous sub-early warning cycle to the predicted data of the power plant's coal inventory in the previous sub-early warning cycle when monitoring the primary early warning data of the power plant's coal inventory or the primary alarm data of the power plant's coal inventory, and record it as the early warning correction ratio of the power plant's coal inventory predicted data in the current sub-early warning cycle; Obtain the power plant coal dispatching data, and perform periodic warning correction on the power plant coal inventory forecast data of the current sub-warning cycle in combination with the sub-warning cycle. The power plant coal dispatching data includes: dispatching data on the amount of coal unloaded but not in stock, dispatching data on incoming coal, and dispatching data on daily consumption; An intelligent early warning unit, used to calculate the secondary power plant coal inventory data in each sub-early warning period within the early warning period according to the power plant coal inventory early warning logic combined with the early warning correction result; ;in, Indicates the first Coal inventory data of secondary power plants within each sub-warning period; Indicates Actual data of coal inventory of power plants in the previous sub-warning cycle; Indicates Coal supply dispatching data within a warning cycle; Indicates Daily consumption dispatch data within each sub-warning cycle; Indicates Dispatching data of coal quantity unloaded but not stored in stock within each sub-warning cycle; Indicates Actual data of coal inventory of power plants in each sub-warning cycle; Indicates Coal inventory forecast data for power plants for each sub-warning cycle; Indicates Input of data features of each sub-warning cycle; represents the weight matrix of the power plant coal inventory forecasting model; Indicates bias; represents the activation function; Indicates New coal dispatching data within a warning cycle; Indicates the total number of sub-warning cycles; When the secondary power plant coal inventory data is within the total power plant coal inventory data of the early warning ratio, generating power plant coal inventory secondary early warning data; The alarm unit is used to generate secondary alarm data of coal inventory in the power plant when the secondary power plant coal inventory data is within the alarm ratio of the total power plant coal inventory data.

[0047] In this embodiment, an early warning period and a safety period for the power plant's coal inventory are set. For example, the early warning period is set to 15 days, that is, the coal inventory data of the power plant for the next 15 days is obtained for early warning judgment. For example, the safety period for the power plant's coal inventory is set to when the power plant's coal inventory for one day can support 7 days or more of use, and the power plant's coal inventory is judged to be safe, then 7 days is the power plant's coal inventory safety period.

[0048] In this embodiment, the coal inventory warning logic of the power plant, for example, calculates the inventory of each day in the next 15 days, where the inventory of the day = the inventory of the previous day + the coal quantity of the day - the daily consumption of the day + the remaining quantity that has been unloaded but not put into the inventory; If the inventory on any day is less than 10 days but more than 7 days, an early warning of the power plant's coal inventory will be issued; If the inventory on any day is less than 7 days, a power plant coal inventory alarm will be issued.

[0049] In this embodiment, each sub-warning cycle within the warning cycle, for example, a warning cycle of 15 days, has 1 day as a sub-warning cycle.

[0050] In this embodiment, the coal inventory data of a primary power plant refers to the coal inventory data of a power plant determined directly according to the coal inventory early warning logic of the power plant and the coal inventory forecast data of the power plant, and is affected by the forecast error of the coal inventory forecast data of the power plant.

[0051] In this embodiment, the amount of coal that has been unloaded but not stored in the inventory, that is, the amount of coal that has arrived at the power plant but has not been counted in the inventory, is included in the data in the next early warning cycle.

[0052] In this embodiment, the incoming coal quantity refers to the amount of coal that is included in the inventory on that day; the daily consumption refers to the amount of coal consumed daily.

[0053] In this embodiment, the coal inventory data of the power plant in the previous warning cycle of the current sub-warning cycle is combined, for example, the actual coal inventory data of the power plant on the previous day is obtained, that is, the authenticity of the coal inventory data of the previous power plant is determined.

[0054] In this embodiment, the total power plant coal inventory data of the early warning period is obtained, for example, the total power plant coal inventory data of the next 15 days is obtained, which is used for subsequent determination of the inventory usage days for each day in the next 15 days.

[0055] In this embodiment, if the current power plant coal inventory data of the current sub-warning cycle is within the total power plant coal inventory data of the warning ratio, the power plant coal inventory first warning data is generated. For example, if the current power plant coal inventory data of the day is within the 7-10 days of use, the power plant coal inventory first warning data is generated.

[0056] In this embodiment, if the current power plant coal inventory data of the current sub-warning cycle is within the total power plant coal inventory data of the alarm ratio, for example, the current power plant coal inventory data of the day is within the 0-7 days of use, then a power plant coal inventory alarm data is generated.

[0057] In this embodiment, the power plant coal inventory primary warning data and the power plant coal inventory primary alarm data are both affected by the prediction error of the power plant coal inventory prediction data.

[0058] In this embodiment, the early warning correction ratio is used to correct the forecast data to ensure the accuracy of the power plant coal inventory early warning data and the power plant coal inventory alarm data.

[0059] In this embodiment, the power plant coal scheduling data is obtained, and the power plant coal inventory forecast data of the current sub-warning cycle is combined with the sub-warning cycle to perform periodic warning correction. For example, the power plant coal inventory forecast data for 15 days is corrected daily based on the power plant coal scheduling data.

[0060] In this embodiment, the secondary power plant coal inventory data refers to the power plant coal inventory data calculated according to the power plant coal inventory early warning logic combined with the early warning correction result, eliminating the impact of the prediction error of the power plant coal inventory forecast data.

[0061] In this embodiment, when the secondary power plant coal inventory data is within the warning ratio of the total power plant coal inventory data, secondary warning data of the power plant coal inventory is generated. For example, the warning period is set to 15 days, the warning ratio is set to 7-10 days, and the alarm ratio is set to 0-7 days. The secondary power plant coal inventory data on that day is within the 7-10 days of usage, and secondary warning data of the power plant coal inventory is generated.

[0062] In this embodiment, the power plant coal inventory secondary early warning data and the power plant coal inventory secondary alarm data refer to early warning data and alarm data that are not affected by the prediction error of the power plant coal inventory prediction data.

[0063] The working principle and beneficial effects of the above technical solution are: by setting the early warning logic, obtaining the power plant's coal dispatching data, and performing early warning correction on the power plant's coal inventory forecast data, when it is determined that the early warning-corrected power plant's coal inventory forecast data matches the early warning logic, intelligent early warning data is generated, thereby achieving efficient and high-quality intelligent early warning of the power plant's coal inventory.

[0064] Embodiment 6: The embodiment of the present invention provides an intelligent early warning system for coal inventory in a power plant, further comprising: Early warning alarm visualization unit, used to build a user visualization interface to display the early warning data of power plant coal inventory or the alarm data of power plant coal inventory in real time; The early warning alarm notification unit is used to generate notification data according to the power plant coal inventory early warning data or the power plant coal inventory alarm data, and send the notification data to relevant administrators according to the preset early warning alarm notification strategy.

[0065] In this embodiment, the user visualization interface is used to allow operators to efficiently view the power plant coal inventory forecast results and the power plant coal inventory early warning alarm data.

[0066] In this embodiment, the notification data, for example, is notification data for notifying an administrator to replenish the coal inventory of a power plant.

[0067] In this embodiment, a warning alarm notification strategy is preset, for example, notifying relevant administrators via SMS, email, system message, etc.

[0068] The working principle and beneficial effects of the above technical solution are: through the visualization and notification of early warning alarms, it is conducive to quickly resolving the early warning alarms of coal inventory in power plants, effectively ensuring the stable operation of power plants.

[0069] Embodiment 7: The embodiment of the present invention provides an intelligent early warning system for coal inventory in a power plant, further comprising: The early warning elimination module is used to execute the preset early warning alarm elimination strategy when monitoring the power plant coal inventory early warning data or the power plant coal inventory alarm data, and generate and explain the actual elimination strategy.

[0070] In this embodiment, a preset early warning alarm elimination strategy is executed, and an actual elimination strategy is generated and explained, which is used to actually and effectively eliminate the power plant's coal inventory early warning data or the power plant's coal inventory alarm data and execute it efficiently. For example, when a power plant issues an excessive inventory warning, the preset early warning elimination strategy of using a ship instead of a warehouse is executed.

[0071] The working principle and beneficial effect of the above technical solution are: by executing the preset early warning alarm elimination strategy, generating and explaining the actual elimination strategy, it is conducive to the practical application and solving the early warning alarm data of the power plant coal inventory.

[0072] Embodiment 8: like Figure 2 As shown, the embodiment of the present invention provides an intelligent early warning method for coal inventory in a power plant, which specifically includes: Step 1: Acquire and pre-process the power plant coal inventory data and the power plant coal inventory impact data in real time, integrate the power plant coal inventory data and the power plant coal inventory impact data acquired in real time and extract data features; Step 2: construct and train a power plant coal inventory forecasting model based on historical power plant coal inventory data combined with time series, input the data features, and generate power plant coal inventory forecasting data; Step 3: Set the early warning logic, obtain the power plant coal dispatching data, and perform early warning correction on the power plant coal inventory forecast data. When it is determined that the early warning corrected power plant coal inventory forecast data matches the early warning logic, generate intelligent early warning data.

[0073] The working principle and beneficial effects of the above technical solution are: by real-time acquisition and preprocessing of power plant coal inventory data and power plant coal inventory impact data, integrating and extracting data features; constructing and training a power plant coal inventory prediction model based on historical power plant coal inventory data combined with time series, inputting the data features, and generating power plant coal inventory prediction data; setting early warning logic, acquiring power plant coal scheduling data, and performing early warning correction on power plant coal inventory prediction data, and generating intelligent early warning data when it is determined that the early warning corrected power plant coal inventory prediction data matches the early warning logic; achieving efficient and high-quality intelligent early warning of power plant coal inventory.

[0074] 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. An intelligent early warning system for coal inventory in a power plant, characterized in that: include: A data acquisition module is used to acquire and pre-process the power plant coal inventory data and the power plant coal inventory impact data in real time, integrate the power plant coal inventory data and the power plant coal inventory impact data acquired in real time and extract data features; A data prediction module is used to construct and train a power plant coal inventory prediction model based on historical power plant coal inventory data combined with time series, input the data features, and generate power plant coal inventory prediction data; The intelligent early warning module is used to set the early warning logic, obtain the coal dispatching data of the power plant, and perform early warning correction on the coal inventory forecast data of the power plant. When it is determined that the early warning corrected coal inventory forecast data of the power plant matches the early warning logic, the intelligent early warning data is generated.

2. The intelligent early warning system for coal inventory in a power plant according to claim 1 is characterized in that: Data acquisition module, including: A data acquisition unit is used to acquire the power plant coal inventory data and the power plant coal inventory impact data in real time, wherein the power plant coal inventory impact data includes: resource implementation data, in-transit transportation data, cycle consumption data and weather change data; A data preprocessing unit is used to clean and convert the real-time coal inventory data and coal in-and-out data of power plants; The data integration unit is used to set data integration categories and classify and integrate the data cleaning and data conversion results, wherein the data integration categories include: power plant coal inventory data category, power plant coal incoming data category, and power plant coal outgoing data category; The data feature extraction unit is used to determine the current warning scenario of the power plant's coal inventory data based on the data integration result, and then extract the data features.

3. The intelligent early warning system for coal inventory in a power plant according to claim 2 is characterized in that: Data feature extraction unit, including: The early warning scenario block is used to obtain the power plant's coal inventory data and the power plant's coal inventory impact data for a second time based on the data integration results, and to determine the current early warning scenario of the power plant's coal inventory data based on historical early warning scenarios. The historical early warning scenarios include: the power plant's imported coal delay early warning scenario, the power plant's domestic trade coal to loading port delay early warning scenario, the power plant's domestic trade coal to loading port excessively long early warning scenario, the power plant's domestic trade coal to unloading port delay early warning scenario and the power plant's coal inventory early warning scenario.

4. The intelligent early warning system for coal inventory in a power plant according to claim 1 is characterized in that: Data prediction module, including: A model building unit is used to select a learning model, build a power plant coal inventory prediction model based on historical power plant coal inventory data combined with time series, and perform data prediction on the power plant coal inventory; A training and verification unit, used to randomly select historical power plant coal inventory data, divide it into a training set, a verification set and a test set, and train the power plant coal inventory prediction model and verify the prediction performance; The model testing unit is used to perform a model test on the power plant coal inventory prediction model that has been trained and verified, input the test data into the power plant coal inventory prediction model that has been trained and verified, and if the output result is consistent with the preset test result, the model test is determined to be qualified; The forecasting data unit is used to input data features into the power plant coal inventory forecasting model that has passed the model test to generate the power plant coal inventory forecasting data.

5. The intelligent early warning system for coal inventory in a power plant according to claim 1 is characterized in that: Intelligent early warning module, including: An early warning logic setting unit is used to divide the coal inventory data of the power plant according to the coal inventory time and the coal inventory type of the power plant, and set the early warning logic of the coal inventory of the power plant; Set an early warning cycle and a power plant coal inventory safety cycle, and calculate the coal inventory data of the power plant in each sub-alert cycle within the early warning cycle according to the early warning logic of the power plant coal inventory; Obtain the amount of coal that has been unloaded but not put into inventory, the amount of incoming coal, and the daily consumption in the current sub-warning cycle, and combine the coal inventory data of the previous power plant in the previous warning cycle of the current sub-warning cycle to determine the current power plant coal inventory data of the current sub-warning cycle; Obtain the total power plant coal inventory data of the early warning period. If the current power plant coal inventory data of the current sub-early warning period is within the total power plant coal inventory data of the early warning ratio, generate the power plant coal inventory early warning data; If the current power plant coal inventory data of the current sub-warning cycle is within the total power plant coal inventory data of the alarm ratio, the power plant coal inventory primary alarm data is generated; An early warning correction unit is used to obtain the data ratio of the actual data of the power plant's coal inventory in the previous sub-early warning cycle to the predicted data of the power plant's coal inventory in the previous sub-early warning cycle when monitoring the primary early warning data of the power plant's coal inventory or the primary alarm data of the power plant's coal inventory, and record it as the early warning correction ratio of the power plant's coal inventory predicted data in the current sub-early warning cycle; Obtain the power plant coal dispatching data, and perform periodic warning correction on the power plant coal inventory forecast data of the current sub-warning cycle in combination with the sub-warning cycle. The power plant coal dispatching data includes: dispatching data on the amount of coal unloaded but not in stock, dispatching data on incoming coal, and dispatching data on daily consumption; An intelligent early warning unit, used to calculate the secondary power plant coal inventory data in each sub-early warning period within the early warning period according to the power plant coal inventory early warning logic combined with the early warning correction result; ;in, Indicates the first Coal inventory data of secondary power plants within each sub-warning period; Indicates Actual data of coal inventory of power plants in the previous sub-warning cycle; Indicates Coal supply dispatching data within a warning cycle; Indicates Daily consumption dispatch data within each sub-warning cycle; Indicates Dispatching data of coal quantity unloaded but not stored in stock within each sub-warning cycle; Indicates Actual data of coal inventory of power plants in each sub-warning cycle; Indicates Coal inventory forecast data for power plants for each sub-warning cycle; Indicates Data feature input for each sub-warning cycle; represents the weight matrix of the power plant coal inventory forecasting model; Indicates bias; represents the activation function; Indicates New coal dispatching data within a warning cycle; Indicates the total number of sub-warning cycles; When the secondary power plant coal inventory data is within the total power plant coal inventory data of the early warning ratio, generating power plant coal inventory secondary early warning data; The alarm unit is used to generate secondary alarm data of coal inventory in the power plant when the secondary power plant coal inventory data is within the alarm ratio of the total power plant coal inventory data.

6. The intelligent early warning system for coal inventory in a power plant according to claim 5 is characterized in that: Also includes: Early warning alarm visualization unit, used to build a user visualization interface to display the early warning data of power plant coal inventory or the alarm data of power plant coal inventory in real time; The early warning alarm notification unit is used to generate notification data according to the power plant coal inventory early warning data or the power plant coal inventory alarm data, and send the notification data to relevant administrators according to the preset early warning alarm notification strategy.

7. The intelligent early warning system for coal inventory in a power plant according to claim 1 is characterized in that: Also includes: The early warning elimination module is used to execute the preset early warning alarm elimination strategy when monitoring the power plant coal inventory early warning data or the power plant coal inventory alarm data, and generate and explain the actual elimination strategy.

8. An intelligent early warning method for coal inventory in a power plant, characterized in that: include: Step 1: Acquire and pre-process the power plant coal inventory data and the power plant coal inventory impact data in real time, integrate the power plant coal inventory data and the power plant coal inventory impact data acquired in real time and extract data features; Step 2: construct and train a power plant coal inventory forecasting model based on historical power plant coal inventory data combined with time series, input the data features, and generate power plant coal inventory forecasting data; Step 3: Set the early warning logic, obtain the power plant coal dispatching data, and perform early warning correction on the power plant coal inventory forecast data. When it is determined that the early warning corrected power plant coal inventory forecast data matches the early warning logic, generate intelligent early warning data.

Images