A monitoring method for blast furnace coal injection system

Abstract

The present invention discloses a monitoring method for a blast furnace coal injection system, which relates to the technical field of data monitoring, including determining the parameter operation sequence between parameters involved in each system according to the operation sequence between a coal conveying system, a coal mill system, a coal injection system and a reaction monitoring system in a blast furnace; constructing the corresponding relationship between parameters according to the parameter operation sequence between parameters involved in each system and the principle between parameters; determining the monitoring function requirements, and obtaining the target evaluation index based on the monitoring function requirements; classifying the degree of deviation according to the deviation between the target evaluation index and the actual evaluation index, and obtaining multiple categories of deviation degrees; constructing multiple data processing strategies based on the corresponding relationship between parameters, establishing the matching relationship between the degree of deviation of each category and multiple data processing strategies, thereby selecting the data processing strategy and performing data processing. The adaptability of different monitoring is improved, the appropriateness of data accuracy is guaranteed, and the monitoring effect is improved.

Description

Technical Field

[0001] The present application relates to the technical field of data monitoring, and more specifically, to a monitoring method for a blast furnace coal injection system. Background Art

[0002] The monitoring background technology of blast furnace coal injection system mainly includes sensor technology, automatic control technology, Internet of Things technology and data analysis technology. Sensing technology monitors the equipment status in real time through sensors such as temperature, pressure and flow, and automatic control technology uses PID control and feedback control to realize intelligent scheduling and operation control of the system. Internet of Things technology realizes information sharing and remote control between components through sensor networks and remote monitoring. Data analysis technology uses machine learning and big data analysis to process real-time data, find problems and optimize system performance. The integration of these technologies improves the intelligence, efficiency and safety of blast furnace coal injection system.

[0003] In the prior art, the monitoring of blast furnace coal injection systems has multiple purposes, such as early warning, fault diagnosis and automatic control. Different purposes have different requirements on data accuracy and processing strategies, and it is impossible to provide a monitoring solution with high adaptability.

[0004] Therefore, how to improve the monitoring adaptability of the blast furnace coal injection system is a technical problem that needs to be solved. Summary of the invention

[0005] The present invention provides a monitoring method for a blast furnace coal injection system, which is used to solve the technical problem of low monitoring adaptability in the prior art. The blast furnace coal injection system includes a coal conveying system, a coal mill system, a coal injection system and a blast furnace reaction monitoring system, and the method includes:

[0006] Determine the parameter operation sequence between the parameters involved in each system according to the operation sequence between the coal conveying system, the coal mill system, the coal injection system and the reaction monitoring system in the blast furnace;

[0007] Construct the corresponding relationship between parameters according to the parameter operation sequence and the principle between parameters involved in each system;

[0008] Determine the monitoring function requirements and obtain target evaluation indicators based on the monitoring function requirements;

[0009] According to the deviation between the target evaluation index and the actual evaluation index, the degree of deviation is classified to obtain multi-category deviation degrees;

[0010] Based on the corresponding relationship between parameters, a variety of data processing strategies are constructed, and a matching relationship between the degree of deviation of each category and a variety of data processing strategies is established, so as to select a data processing strategy for data processing.

[0011] In some embodiments of the present application, the corresponding relationship between parameters is established according to the parameter operation sequence and the principle between parameters involved in each system, including:

[0012] If the principle between the parameters only involves parameters involved in two systems with adjacent parameter operation sequences, a first weight and a first threshold are determined according to specific adjacent parameter categories, and a first calculation relationship is determined based on the first weight and the first threshold;

[0013] Otherwise, the parameters involved in the principle are recorded as common parameters, the second weight, the influencing factor and the second threshold are determined according to the parameter category of the common parameter, and the second calculation relationship is determined according to the second weight, the influencing factor and the second threshold.

[0014] In some embodiments of the present application, determining the first calculation relationship based on the first weight and the first threshold includes:

[0015] Determine the original calculation relationship between the two system parameters based on the principle between the parameters;

[0016] Calculate the correlation between the remaining parameters and the two system parameters, retain the parameters with correlation greater than the first threshold, and sort these parameters by correlation;

[0017] The number of intervals is determined based on the difference between the first and last relevances;

[0018] Divide the sorting into batches according to the number of intervals, and assign weights according to the relevance of each parameter in each batch;

[0019] The original calculation relationship is adjusted based on the allocation weight and the parameter size to obtain multiple first calculation relationships.

[0020] In some embodiments of the present application, determining the second calculation relationship according to the second weight, the impact factor and the second threshold includes:

[0021] Determine the original calculation relationship based on the principle between common parameters;

[0022] Calculate the correlation between the remaining parameters and the common parameter, retain the parameters with correlation greater than the second threshold, and sort these parameters by correlation;

[0023] The number of intervals is determined based on the difference between the first and last relevances;

[0024] Divide the sorting into batches according to the number of intervals, and assign weights according to the relevance of each parameter in each batch;

[0025] The original calculation relationship is adjusted based on the allocation weight, the influencing factor and the parameter size to obtain multiple second calculation relationships.

[0026] In some embodiments of the present application, determining the monitoring function requirements and obtaining the target evaluation index based on the monitoring function requirements include:

[0027] Monitoring function requirements include early warning, fault diagnosis, automated control and evaluation;

[0028] Early warning, fault diagnosis, automated control and evaluation each correspond to different multiple target evaluation indicators.

[0029] In some embodiments of the present application, the degree of deviation is classified according to the deviation between the target evaluation index and the actual evaluation index to obtain multiple categories of deviation degrees, including:

[0030] Determine the total accuracy based on the system accuracy involved according to the monitoring function requirements;

[0031] Based on the total accuracy, multiple deviation intervals are determined, and the deviations between the target evaluation index and the actual evaluation index are classified according to the multiple deviation intervals to obtain multi-category deviation degrees.

[0032] In some embodiments of the present application, a variety of data processing strategies are constructed based on the corresponding relationship between parameters, including:

[0033] A plurality of data processing strategies are constructed according to the plurality of first calculation relationships, the plurality of second calculation relationships and the corresponding preset algorithms.

[0034] In some embodiments of the present application, a matching relationship between the degree of deviation of each category and a plurality of data processing strategies is established, including:

[0035] The prediction model is used to predict the optimal data processing strategy corresponding to each category deviation degree among multiple data processing strategies, and a matching relationship between each category deviation degree and multiple data processing strategies is established.

[0036] By applying the above technical solutions, the parameter operation order between the parameters involved in each system is determined according to the operation order between the coal transportation system, coal mill system, coal injection system and blast furnace reaction monitoring system; the corresponding relationship between the parameters is constructed according to the parameter operation order between the parameters involved in each system and the principle between the parameters; the monitoring function requirements are determined, and the target evaluation index is obtained based on the monitoring function requirements; the deviation degree is classified according to the deviation between the target evaluation index and the actual evaluation index, and the multi-category deviation degree is obtained; multiple data processing strategies are constructed based on the corresponding relationship between the parameters, and the matching relationship between the deviation degree of each category and multiple data processing strategies is established, so as to select the data processing strategy and perform data processing. The adaptability of different monitoring is improved, the appropriateness of data accuracy is ensured, and the monitoring effect is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 A flow chart of a monitoring method for a blast furnace coal injection system proposed in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0040] The present application embodiment provides a monitoring method for a blast furnace coal injection system, such as Figure 1 As shown, the blast furnace coal injection system includes a coal conveying system, a coal mill system, a coal injection system and a blast furnace reaction monitoring system, and the method includes the following steps:

[0041] Step S101, determining the parameter operation sequence among the parameters involved in each system according to the operation sequence among the coal conveying system, the coal mill system, the coal injection system and the blast furnace reaction monitoring system.

[0042] In this embodiment, in the blast furnace coal injection system, the operation sequence between the various components is generally carried out according to the following process:

[0043] Pulverized coal conveying system: This is the initial stage of conveying pulverized coal from the storage location to the coal injection system near the blast furnace. The pulverized coal is sent to the subsequent processing stage through the conveying pipeline.

[0044] Coal pulverizer: After being transported to the coal pulverizer, the original coal powder is mechanically ground to a fineness suitable for coal injection. The purpose of this stage is to improve the reactivity and adaptability of the coal powder.

[0045] Coal injection device: The treated pulverized coal is injected into the furnace cavity of the blast furnace through coal injection devices, such as coal injection guns and coal injection pipes. This stage is the core of the entire system. The pulverized coal acts as a reducing agent in the blast furnace and participates in the smelting process.

[0046] Blast furnace reaction monitoring system: used to monitor the reaction conditions in the blast furnace.

[0047] In this embodiment, the system operation sequence is coal conveying system - coal mill system - coal injection system - blast furnace reaction monitoring system. The parameter operation sequence is coal conveying system parameters - coal mill system parameters - coal injection system parameters - blast furnace reaction monitoring system parameters.

[0048] Step S102, building a corresponding relationship between parameters according to the parameter operation sequence and the principle between parameters involved in each system.

[0049] In this embodiment, the principle between the parameters refers to having a certain mathematical or physical relationship, for example:

[0050] Pulverized coal conveying system:

[0051] Flow rate: The flow rate of the conveying system is a key parameter, which directly affects the subsequent investment in coal powder mills.

[0052] Pressure: The pressure of the delivery pipeline needs to be maintained within an appropriate range to ensure that the pulverized coal can flow stably.

[0053] Pulverized coal mill:

[0054] Coal mill speed: The speed of the coal mill will affect the fineness of the coal powder and needs to be adjusted according to requirements.

[0055] Feed rate: Controlling the feed rate can adjust the output of the coal mill and affect the subsequent coal injection process.

[0056] Coal mill load: Changes in load will affect mechanical wear and energy consumption.

[0057] Coal injection device:

[0058] Coal injection amount: It is the key parameter of the coal injection system and directly determines the amount of coal powder input into the blast furnace.

[0059] Nozzle status: Nozzle wear, blockage and other conditions will affect the uniformity and stability of coal injection.

[0060] In some embodiments of the present application, the corresponding relationship between parameters is established according to the parameter operation sequence and the principle between parameters involved in each system, including:

[0061] If the principle between the parameters only involves parameters involved in two systems with adjacent parameter operation sequences, a first weight and a first threshold are determined according to specific adjacent parameter categories, and a first calculation relationship is determined based on the first weight and the first threshold;

[0062] Otherwise, the parameters involved in the principle are recorded as common parameters, the second weight, the influencing factor and the second threshold are determined according to the parameter category of the common parameter, and the second calculation relationship is determined according to the second weight, the influencing factor and the second threshold.

[0063] In this embodiment, if the principle between the parameters only involves the parameters involved in two systems with adjacent parameter operation sequences, it means that this principle relationship is the relationship between two adjacent systems and does not involve other systems. The first calculation relationship includes the principle relationship and the correction of the principle relationship by the influence of other parameters. The first weight is the weight of the influence of other parameters. In addition to the principle relationship, other parameters may have a smaller impact on the parameters in the principle relationship and need to be taken into account. The first threshold is the correlation threshold between other parameters and parameters. Different specific adjacent parameter categories correspond to different first weights and first thresholds.

[0064] In this embodiment, if the principle between parameters only involves parameters involved in multiple systems, it is necessary to consider the impact between the multiple systems and describe it with an impact factor.

[0065] In some embodiments of the present application, determining the first calculation relationship based on the first weight and the first threshold includes:

[0066] Determine the original calculation relationship between the two system parameters based on the principle between the parameters;

[0067] Calculate the correlation between the remaining parameters and the two system parameters, retain the parameters with correlation greater than the first threshold, and sort these parameters by correlation;

[0068] The number of intervals is determined based on the difference between the first and last relevances;

[0069] Divide the sorting into batches according to the number of intervals, and assign weights according to the relevance of each parameter in each batch;

[0070] The original calculation relationship is adjusted based on the allocation weight and the parameter size to obtain multiple first calculation relationships.

[0071] In this embodiment, the original calculation relationship is adjusted based on the allocation weight and the parameter size. For example, the original calculation relationship is f(x), f(x)*a function of the sum of the products of the allocation weight and the corresponding parameters (the degree of influence of the total influence amount). The same applies to the subsequent steps. The multiple first calculation relationships represent parameter relationships of different precisions.

[0072] In some embodiments of the present application, determining the second calculation relationship according to the second weight, the impact factor and the second threshold includes:

[0073] Determine the original calculation relationship based on the principle between common parameters;

[0074] Calculate the correlation between the remaining parameters and the common parameter, retain the parameters with correlation greater than the second threshold, and sort these parameters by correlation;

[0075] The number of intervals is determined based on the difference between the first and last relevances;

[0076] Divide the sorting into batches according to the number of intervals, and assign weights according to the relevance of each parameter in each batch;

[0077] The original calculation relationship is adjusted based on the allocation weight, the influencing factor and the parameter size to obtain multiple second calculation relationships.

[0078] In this embodiment, the original calculation relationship is adjusted based on the allocation weight, influence factor, and parameter size. For example, the original calculation relationship is f(x), where f(x)*a function of the sum of the products of the allocation weight and the corresponding parameters*influence factor (the degree of influence of the total influence).

[0079] Step S103, determining monitoring function requirements, and obtaining target evaluation indicators based on the monitoring function requirements.

[0080] In some embodiments of the present application, determining the monitoring function requirements and obtaining the target evaluation index based on the monitoring function requirements include:

[0081] Monitoring function requirements include early warning, fault diagnosis, automated control and evaluation;

[0082] Early warning, fault diagnosis, automated control and evaluation each correspond to different multiple target evaluation indicators.

[0083] In this embodiment, the monitoring function requirements include early warning, fault diagnosis, automatic control and evaluation, etc. In the monitoring method of the blast furnace coal injection system, there are some different requirements for monitoring data in different aspects such as early warning, fault diagnosis, control, and evaluation:

[0084] Early warning system:

[0085] Data nature requirements: Real-time performance is key, and key parameters need to be continuously monitored to ensure that early warning information can be issued in a timely manner.

[0086] Threshold setting: The warning threshold needs to be set reasonably according to the stability and security of the system to ensure that problems can be discovered in time and false alarms can be reduced.

[0087] Troubleshooting:

[0088] Data nature requirements: In addition to real-time performance, high-precision and high-resolution data are also required for accurate fault diagnosis.

[0089] Data history: Historical data needs to be retained to train machine learning algorithms and improve the ability to identify abnormal situations.

[0090] Automation control:

[0091] Real-time and reliability: The control system needs to monitor and respond in real time to ensure that the system's automated scheduling can adjust operating parameters in a timely manner.

[0092] Feedback mechanism: Data needs to be fed back to the control system in a timely manner so that the system can make corresponding adjustments based on actual conditions.

[0093] Energy efficiency assessment:

[0094] Data nature requirements: Data on aspects such as energy consumption are required in order to accurately evaluate the energy efficiency of the system.

[0095] Key Performance Indicators: Key energy efficiency indicators, such as energy consumption per unit of output, need to be defined and monitored for evaluation and improvement.

[0096] In this embodiment, the evaluation indicators corresponding to different monitoring function requirements include:

[0097] Early warning system:

[0098] Accuracy: The accuracy of the warning is a key indicator for evaluating the system, that is, whether the system can correctly identify potential problems.

[0099] Timeliness: Measures the speed at which the system issues an early warning, that is, how quickly a response can be given after a problem occurs.

[0100] Troubleshooting:

[0101] Accuracy: Measures the degree to which the fault diagnosis system correctly identifies abnormal situations.

[0102] False positive rate: Indicates the extent to which the system mistakenly judges normal situations as abnormal.

[0103] Automation control:

[0104] Response time: measures the system's ability to respond quickly to real-time data changes.

[0105] Control accuracy: refers to the accuracy with which the system adjusts operating parameters to ensure efficient production.

[0106] Energy efficiency assessment:

[0107] Energy consumption per unit of output: measures the energy consumed to produce each unit of product, used to evaluate the energy efficiency of the system.

[0108] Energy utilization rate: evaluates the system's effective use of energy.

[0109] Step S104, classifying the degree of deviation according to the deviation between the target evaluation index and the actual evaluation index to obtain multiple categories of deviation degrees.

[0110] In this embodiment, the multi-category deviation degree is that each category deviation degree is a deviation interval.

[0111] In some embodiments of the present application, the degree of deviation is classified according to the deviation between the target evaluation index and the actual evaluation index to obtain multiple categories of deviation degrees, including:

[0112] Determine the total accuracy based on the system accuracy involved according to the monitoring function requirements;

[0113] Based on the total accuracy, multiple deviation intervals are determined, and the deviations between the target evaluation index and the actual evaluation index are classified according to the multiple deviation intervals to obtain multi-category deviation degrees.

[0114] In this embodiment, different total accuracies correspond to different multiple deviation intervals.

[0115] Step S105, constructing a plurality of data processing strategies based on the corresponding relationship between the parameters, establishing a matching relationship between the degree of deviation of each category and the plurality of data processing strategies, thereby selecting a data processing strategy and performing data processing.

[0116] In this embodiment, multiple data processing strategies are constructed, and a matching relationship between each strategy and the degree of category deviation is established.

[0117] In some embodiments of the present application, a variety of data processing strategies are constructed based on the corresponding relationship between parameters, including:

[0118] A plurality of data processing strategies are constructed according to the plurality of first calculation relationships, the plurality of second calculation relationships and the corresponding preset algorithms.

[0119] In some embodiments of the present application, a matching relationship between the degree of deviation of each category and a plurality of data processing strategies is established, including:

[0120] The prediction model is used to predict the optimal data processing strategy corresponding to each category deviation degree among multiple data processing strategies, and a matching relationship between each category deviation degree and multiple data processing strategies is established.

[0121] By applying the above technical solutions, the parameter operation order between the parameters involved in each system is determined according to the operation order between the coal transportation system, coal mill system, coal injection system and blast furnace reaction monitoring system; the corresponding relationship between the parameters is constructed according to the parameter operation order between the parameters involved in each system and the principle between the parameters; the monitoring function requirements are determined, and the target evaluation index is obtained based on the monitoring function requirements; the deviation degree is classified according to the deviation between the target evaluation index and the actual evaluation index, and the multi-category deviation degree is obtained; multiple data processing strategies are constructed based on the corresponding relationship between the parameters, and the matching relationship between the deviation degree of each category and multiple data processing strategies is established, so as to select the data processing strategy and perform data processing. The adaptability of different monitoring is improved, the appropriateness of data accuracy is ensured, and the monitoring effect is improved.

[0122] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A monitoring method for a blast furnace coal injection system, wherein the blast furnace coal injection system comprises a coal conveying system, a coal mill system, a coal injection system and a blast furnace reaction monitoring system, It is characterized in that The method comprises: Determine the parameter operation sequence between the parameters involved in each system according to the operation sequence between the coal conveying system, the coal mill system, the coal injection system and the reaction monitoring system in the blast furnace; Construct the corresponding relationship between parameters according to the parameter operation sequence and the principle between parameters involved in each system; Determine the monitoring function requirements and obtain target evaluation indicators based on the monitoring function requirements; According to the deviation between the target evaluation index and the actual evaluation index, the degree of deviation is classified to obtain multi-category deviation degrees; Based on the corresponding relationship between parameters, a variety of data processing strategies are constructed, and the matching relationship between the degree of deviation of each category and a variety of data processing strategies is established, so as to select a data processing strategy and perform data processing; The corresponding relationship between parameters is established according to the parameter operation sequence and the principle between parameters involved in each system, including: If the principle between the parameters only involves parameters involved in two systems with adjacent parameter operation sequences, a first weight and a first threshold are determined according to parameter categories involved in the two systems with adjacent parameter operation sequences, and a first calculation relationship is determined based on the first weight and the first threshold; Otherwise, the parameters involved in the principle are recorded as common parameters, a second weight, an influencing factor and a second threshold are determined according to the parameter category of the common parameter, and a second calculation relationship is determined according to the second weight, the influencing factor and the second threshold; Determining a first calculation relationship based on a first weight and a first threshold includes: Determine the first original calculation relationship between the parameters involved in two systems with adjacent parameter operation sequences according to the principle between the parameters; Calculate the correlation between the remaining parameters and the parameters involved in the two systems adjacent in the parameter operation order, retain the parameters with correlation greater than the first threshold, and sort these parameters by correlation; The number of intervals is determined based on the difference between the first and last relevances; Divide the sorting into batches according to the number of intervals, and assign weights according to the relevance of each parameter in each batch; Adjust the first original calculation relationship based on the allocation weight and the parameter size to obtain multiple first calculation relationships; And determining a second calculation relationship according to the second weight, the impact factor and the second threshold, including: Determining a second original calculation relationship based on the principle between the common parameters; Calculate the correlation between the remaining parameters and the common parameter, retain the parameters with correlation greater than the second threshold, and sort these parameters by correlation; The number of intervals is determined based on the difference between the first and last relevances; Divide the sorting into batches according to the number of intervals, and assign weights according to the relevance of each parameter in each batch; The second original calculation relationship is adjusted based on the allocation weight, the influence factor and the parameter size to obtain multiple second calculation relationships; Based on the corresponding relationship between parameters, a variety of data processing strategies are constructed, including: A plurality of data processing strategies are constructed according to the plurality of first calculation relationships, the plurality of second calculation relationships and the corresponding preset algorithms.

2. The monitoring method for a blast furnace coal injection system according to claim 1, It is characterized in that Determine the monitoring function requirements and obtain target evaluation indicators based on the monitoring function requirements, including: Monitoring function requirements include early warning, fault diagnosis, automated control and evaluation; Early warning, fault diagnosis, automated control and evaluation each correspond to different multiple target evaluation indicators.

3. The monitoring method for a blast furnace coal injection system according to claim 1, It is characterized in that According to the deviation between the target evaluation index and the actual evaluation index, the deviation degree is classified to obtain multiple categories of deviation degrees, including: Determine the total accuracy based on the system accuracy involved in the monitoring function requirements; Based on the total accuracy, multiple deviation intervals are determined, and the deviations between the target evaluation index and the actual evaluation index are classified according to the multiple deviation intervals to obtain multi-category deviation degrees.

4. The monitoring method for a blast furnace coal injection system according to claim 1, It is characterized in that Establish matching relationships between the degree of deviation of each category and multiple data processing strategies, including: The prediction model is used to predict the optimal data processing strategy corresponding to each category deviation degree among multiple data processing strategies, and a matching relationship between each category deviation degree and multiple data processing strategies is established.

Images