Coal mill operation fault intelligent monitoring system based on artificial intelligence

Abstract

The invention discloses a coal mill operation fault intelligent monitoring system based on artificial intelligence, and belongs to the technical field of equipment operation fault monitoring. The method is used for solving the technical problem that in an existing scheme, due to hysteresis of hydraulic oil granularity anomaly detection and analysis, the autonomous supervision and treatment effect of hydraulic oil granularity anomaly is poor when a coal mill runs. According to the method, monitoring and data statistics are respectively carried out on different fault auxiliary indexes and fault main indexes during operation of the coal mill, and monitoring statistical data corresponding to the different fault auxiliary indexes and the fault main indexes are processed and combined; the abnormal state of the hydraulic oil granularity is determined according to the first influence integrated processing data and the second influence integrated processing data of the multi-dimensional integrated analysis during the operation of the coal mill by carrying out abnormal effective verification analysis and abnormal influence multi-dimensional integrated analysis on the fault index monitoring processing data during the operation of the coal mill, and the abnormal state of the hydraulic oil granularity is determined according to the first influence integrated processing data and the second influence integrated processing data of the multi-dimensional integrated analysis during the operation of the coal mill. And targeted risk prevention management is carried out according to the abnormal state of the hydraulic oil granularity.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment operation fault monitoring, and particularly to an intelligent monitoring system for the operation faults of a coal mill based on artificial intelligence. Background Art

[0002] A coal mill is a key device used in thermal power plants, the cement industry, and other industries to grind solid fuels such as coal into fine powder. Its normal operation is crucial for ensuring the stability and efficiency of the production process.

[0003] When implementing the existing monitoring solutions for the operation faults of a coal mill, for the detection of abnormal hydraulic oil particle size, it still stays at the alarm mechanism where when the detected particle size of the hydraulic oil exceeds the preset threshold, the system will trigger an alarm to notify the maintenance personnel. However, in the early stage when the abnormal hydraulic oil particle size is discovered, it has already had various impacts on the operation of the coal mill, resulting in the lag in the detection and analysis of the abnormal hydraulic oil particle size, and the poor effect of the autonomous supervision and handling of the abnormal hydraulic oil particle size during the operation of the coal mill. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent monitoring system for the operation faults of a coal mill based on artificial intelligence, aiming to solve the technical problem that in the existing solutions, the lag in the detection and analysis of the abnormal hydraulic oil particle size leads to the poor effect of the autonomous supervision and handling of the abnormal hydraulic oil particle size during the operation of the coal mill.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] An intelligent monitoring system for the operation faults of a coal mill based on artificial intelligence includes a multi-dimensional monitoring data processing module for equipment operation, which is used to monitor and statistically analyze different fault secondary indicators and fault primary indicators during the operation of the coal mill, and process and combine the monitoring and statistical data corresponding to different fault secondary indicators and fault primary indicators to obtain fault indicator monitoring and processing data;

[0007] A multi-dimensional data analysis module for equipment operation processing, which is used to conduct effective verification analysis of abnormalities and multi-dimensional integration analysis of abnormal impacts on the fault indicator monitoring and processing data during the operation of the coal mill, to obtain the first impact integration and processing data and the second impact integration and processing data corresponding to the fault indicator monitoring and processing data;

[0008] Among them, traverse and analyze the fault indicator monitoring and processing data during the operation of the coal mill. If there is no element with a value of 1, generate a local normal operation state and give a prompt;

[0009] If there is an element with a value of 1 at the first position, generate an abnormal particle size and give a prompt;

[0010] If there is an element with a non-first digit value of 1, then perform an anomaly-effective verification analysis on the anomaly sub-indicators corresponding to the elements with a value of 1, obtain the real-time operation monitoring data corresponding to the anomaly sub-indicators, and display and connect the real-time operation monitoring data through a preset operation coordinate system to obtain the real-time operation monitoring curve corresponding to the anomaly sub-indicator;

[0011] Monitor the real-time operation monitoring curve and the operation standard data range in the operation coordinate system, obtain the monitoring anomaly value enclosed by the real-time operation monitoring curve outside the operation standard data range. If the monitoring anomaly value is 0, generate a verification analysis normal state and prompt, and at the same time re-mark the anomaly sub-indicator as a normal sub-indicator and do not perform a multi-dimensional integration analysis of the anomaly impact;

[0012] If the monitoring anomaly value is not 0, then perform a multi-dimensional integration analysis of the anomaly impact to obtain the first impact integration processing data and the second impact integration processing data corresponding to different dimension integration analyses;

[0013] The equipment operation fault monitoring and evaluation management module is used to determine the abnormal state of the hydraulic oil particle size according to the first impact integration processing data and the second impact integration processing data of the multi-dimensional integration analysis during the operation of the coal mill, and implement targeted risk prevention management according to the abnormal state of the hydraulic oil particle size.

[0014] Preferably, monitor and statistically analyze the operation of the coal mill according to a preset number of fault sub-indicators. When processing and analyzing the single monitoring and statistical status corresponding to the several fault sub-indicators, sequentially analyze the monitoring and statistical data corresponding to different fault sub-indicators through the sub-indicator recognition model, and output the corresponding sub-indicator status value FZj;

[0015] Among them, the expression of the sub-indicator recognition model is In the formula, j is different fault sub-indicators, j = 1, 2, 3,..., m; m is a positive integer; FSj is the monitoring and statistical data corresponding to different fault sub-indicators; Uj is the operation standard data range corresponding to different fault sub-indicators;

[0016] Mark the sub-indicator as a normal sub-indicator according to the sub-indicator status value of 0;

[0017] Mark the sub-indicator as an abnormal sub-indicator according to the sub-indicator status value of 1.

[0018] Preferably, obtain the monitoring and statistical data corresponding to the fault main indicator, and compare and judge it with the preset fault standard threshold;

[0019] If the value in the monitoring and statistical data is less than the fault standard threshold, set the monitoring identifier corresponding to the fault main indicator to 0;

[0020] Otherwise, set the monitoring flag corresponding to the main fault index to 1;

[0021] Sort and combine the monitoring flag corresponding to the main fault index and the sub-index status values corresponding to different secondary fault indexes to obtain the fault index monitoring and processing data.

[0022] Preferably, when performing multi-dimensional integration analysis of abnormal impacts, through the formula Calculate to obtain the abnormal verification value YH corresponding to the abnormal secondary index; in the formula, JY is the monitoring abnormal value; T is the time difference between the start of the verification analysis of the abnormal secondary index and the acquisition of the last monitoring area; BB is the monitoring abnormal standard value corresponding to the abnormal secondary index.

[0023] If the abnormal verification value is less than or equal to 1, generate a mild abnormal state of verification analysis and prompt, and at the same time re-mark the abnormal secondary index as a mildly abnormal verification secondary index;

[0024] If the abnormal verification value is greater than 1, generate a severe abnormal state of verification analysis and prompt, and at the same time re-mark the abnormal secondary index as a severely abnormal verification secondary index.

[0025] Preferably, when performing integration analysis of the abnormal impact during the operation of the coal mill according to the verification analysis data of abnormal effectiveness, the mildly abnormal verification secondary index and the severely abnormal verification secondary index in the verification analysis data are calculated through the formula Calculate to obtain the impact integration value YZ; in the formula, i is different mildly abnormal verification secondary indexes and severely abnormal verification secondary indexes, i = 1, 2, 3,..., n; n is a positive integer; JHi is the abnormal verification value corresponding to different mildly abnormal verification secondary indexes and severely abnormal verification secondary indexes; ai is the index impact coefficient corresponding to different mildly abnormal verification secondary indexes and severely abnormal verification secondary indexes; YB is the impact integration standard value.

[0026] Preferably, if the impact integration value is empty, generate a normal state of impact integration;

[0027] If the impact integration value is less than or equal to 1, generate a mild abnormal state of impact integration;

[0028] If the impact integration value is greater than 1, generate a severe abnormal state of impact integration;

[0029] Sort and combine the obtained impact integration value with the obtained normal state of impact integration, mild abnormal state of impact integration or severe abnormal state of impact integration to obtain the first impact integration processing data.

[0030] Preferably, count the total number of moderately abnormal sub-indicators and the total number of severely abnormal sub-indicators in the verification and analysis data respectively, and mark them as the first abnormal total and the second abnormal total respectively. Then, analyze the first abnormal total and the second abnormal total through an abnormal integration recognition model to output the corresponding influence integration status value ZZ.

[0031] Among them, the expression of the abnormal integration recognition model is In the formula, N1 and N2 are the first abnormal total and the second abnormal total respectively; N11 and N22 are the standard values of the first abnormal total and the second abnormal total respectively.

[0032] The influence integration status value includes numerical values of 0, 1, or 2.

[0033] Preferably, generate an influence integration normal status according to the influence integration status value with a numerical value of 0.

[0034] Generate an influence integration moderately abnormal status according to the influence integration status value with a numerical value of 1.

[0035] Generate an influence integration severely abnormal status according to the influence integration status value with a numerical value of 2.

[0036] Sort and combine the obtained influence integration status value with the obtained influence integration normal status, influence integration moderately abnormal status, or influence integration severely abnormal status to obtain the second influence integration processing data.

[0037] Preferably, perform a traversal analysis on the obtained first influence integration processing data and the second influence integration processing data.

[0038] If the influence integration severely abnormal status does not exist simultaneously in the traversal results, implement a targeted first risk prevention and management plan.

[0039] Otherwise, implement a targeted second risk prevention and management plan.

[0040] Preferably, obtain all the areas enclosed by the real-time operation monitoring curve outside the operation standard data range, sum up all the areas, and set it as the monitoring abnormal value.

[0041] Compared with the existing solutions, the beneficial effects achieved by the present invention are:

[0042] The present invention monitors and statistically analyzes different secondary fault indicators and primary fault indicators during the operation of the coal mill, and processes and combines the monitoring and statistical data corresponding to different secondary fault indicators and primary fault indicators, realizing the active supervision and analysis of the influence data in different aspects on the operation of the coal mill in the early stage when the abnormal particle size of the hydraulic oil is detected. Furthermore, it can provide reliable local supervision and processing data support for the multi-dimensional analysis and management of the abnormal particle size of the hydraulic oil in the coal mill in the future.

[0043] The present invention realizes the diverse and comprehensive supervision, processing and analysis of the operation of the coal mill by performing abnormal and effective verification analysis and multi-dimensional integration analysis of the influence of the fault index monitoring and processing data during the operation of the coal mill, improving the multi-level supervision and analysis effect of the abnormal particle size of the hydraulic oil during the operation of the coal mill.

[0044] The present invention determines the abnormal state of the particle size of the hydraulic oil according to the first influence integration processing data and the second influence integration processing data of the multi-dimensional integration analysis during the operation of the coal mill, and implements targeted risk prevention management according to the abnormal state of the particle size of the hydraulic oil, realizing the active multi-dimensional supervision and processing management in the early stage when the abnormal particle size of the hydraulic oil occurs and has an impact, and improving the self-supervision and processing effect of the abnormal particle size of the hydraulic oil during the operation of the coal mill. Brief Description of the Drawings

[0045] The following further describes the present invention with reference to the accompanying drawings.

[0046] Figure 1 It is a block diagram of the modules of an intelligent monitoring system for the operation faults of a coal mill based on artificial intelligence according to the present invention.

[0047] Figure 2 It is a flow block diagram of the operation of an intelligent monitoring system for the operation faults of a coal mill based on artificial intelligence according to the present invention.

[0048] Figure 3 It is a flow block diagram for traversing and analyzing the fault index monitoring and processing data during the operation of the coal mill according to the present invention. Detailed Embodiments

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0050] Such as Figures 1 to 2As shown in the figure, the present invention is an intelligent monitoring system for the operation faults of a coal mill based on artificial intelligence, including a multi-dimensional monitoring data processing module for equipment operation, a multi-dimensional data analysis module for equipment operation, and a monitoring, evaluation and management module for equipment operation faults;

[0051] The multi-dimensional monitoring data processing module for equipment operation is used to monitor and statistically analyze different secondary fault indicators and primary fault indicators during the operation of the coal mill, and process and combine the monitoring and statistical data corresponding to different secondary fault indicators and primary fault indicators to obtain processed data of fault indicator monitoring; including:

[0052] Monitor the operation of the coal mill and statistically analyze the data according to a number of preset secondary fault indicators;

[0053] Among them, the number of preset secondary fault indicators includes but is not limited to filter differential pressure, hydraulic oil temperature, actual flow rate through hydraulic components, pressure change of the hydraulic system, and response time of the actuator;

[0054] The filter differential pressure is specifically to monitor the pressure difference across the filter; as wear products enter the hydraulic oil, the filter element will become clogged faster, resulting in an increase in the differential pressure; this is an important sign for early identification of wear;

[0055] The hydraulic oil temperature is specifically to monitor the temperature of the hydraulic oil through a temperature sensor; as the friction increases, more heat is generated, resulting in a local temperature rise; a continuously rising temperature may be an indicator of wear;

[0056] The actual flow rate through hydraulic components is specifically to use a flow meter to measure the actual flow rate through hydraulic components; if a decrease in flow rate is found, it may mean there is internal leakage or blockage of the flow path, both of which are forms of wear;

[0057] The pressure change of the hydraulic system is specifically that wear will cause an increase in internal leakage, resulting in unstable working pressure, manifested as increased pressure fluctuations or abnormal pressure peaks.

[0058] The response time of the actuator is specifically to monitor the response speed of the hydraulic system; wear may cause a decrease in control accuracy, making the movement of the actuator slow and the response time long;

[0059] The primary fault indicator is specifically to detect the particle size of the hydraulic oil;

[0060] When processing and analyzing the single monitoring and statistical status corresponding to a number of secondary fault indicators, the monitoring and statistical data corresponding to different secondary fault indicators are sequentially analyzed through the secondary indicator recognition model, and the corresponding secondary indicator status value FZj is output;

[0061] Among them, the expression of the secondary indicator recognition model is In the formula, j represents different secondary fault indicators, where j = 1, 2, 3, ……, m; m is a positive integer and represents the total number of all secondary fault indicators; FSj represents the monitoring and statistical data corresponding to different secondary fault indicators; Uj represents the operating standard data range corresponding to different secondary fault indicators, and the operating standard data range corresponding to different secondary fault indicators is determined according to the design parameters of the coal mill or can also be determined according to the previous test data of the coal mill;

[0062] It should be noted that the secondary indicator status value is used to monitor, statistically process, and calculate the operating data corresponding to the secondary fault indicators that will be affected when the hydraulic oil particle size is abnormal, so as to digitally represent the real-time secondary indicator status corresponding to the secondary fault indicators;

[0063] The secondary indicator status value includes a numerical value of 0 or 1;

[0064] According to the secondary indicator status value with a numerical value of 0, the secondary indicator to which it belongs is marked as a normal secondary indicator;

[0065] According to the secondary indicator status value with a numerical value of 1, the secondary indicator to which it belongs is marked as an abnormal secondary indicator;

[0066] In addition, obtain the monitoring and statistical data corresponding to the primary fault indicator and compare it with the preset fault standard threshold, and the fault standard threshold is determined according to the design parameters of the coal mill;

[0067] If the numerical value in the monitoring and statistical data is less than the fault standard threshold, set the monitoring identifier corresponding to the primary fault indicator to 0;

[0068] Conversely, set the monitoring identifier corresponding to the primary fault indicator to 1;

[0069] Among them, the monitoring influence weight of the primary fault indicator is greater than the monitoring influence weights of all secondary fault indicators;

[0070] Sort and combine the monitoring identifier corresponding to the primary fault indicator and the secondary indicator status values corresponding to different secondary fault indicators to obtain the fault indicator monitoring and processing data;

[0071] In the embodiment of the present invention, by respectively monitoring and statistically processing different secondary fault indicators and primary fault indicators during the operation of the coal mill, and processing and combining the monitoring and statistical data corresponding to different secondary fault indicators and primary fault indicators, it realizes that in the early stage when the abnormal hydraulic oil particle size is discovered, the influence data in different aspects on the operation of the coal mill has been actively supervised and analyzed, and thus can provide reliable local supervision and processing data support for the multi-dimensional analysis and management of the abnormal hydraulic oil particle size of the coal mill in the future.

[0072] The device runs a multi-dimensional processing data analysis module, which is used to perform abnormal and effective verification analysis and multi-dimensional integration analysis of the abnormal impact on the data of the fault index monitoring during the operation of the coal mill, and obtain the first impact integration processing data and the second impact integration processing data corresponding to the fault index monitoring processing data; including:

[0073] As Figure 3 shown, traverse and analyze the data of the fault index monitoring during the operation of the coal mill. If there is no element with a value of 1, generate a local normal operation state and prompt;

[0074] If the value of the first element is 1, generate a granularity anomaly and prompt;

[0075] If there is an element with a non-first value of 1, perform abnormal and effective verification analysis on the abnormal sub-index corresponding to the element with a value of 1, obtain the real-time operation monitoring data corresponding to the abnormal sub-index, and display and connect the real-time operation monitoring data through a preset operation coordinate system to obtain the real-time operation monitoring curve corresponding to the abnormal sub-index;

[0076] Among them, the horizontal axis of the operation coordinate system is the real-time changing Beijing time, with the unit accurate to seconds, and the vertical axis is the standard operation value arranged in an arithmetic progression corresponding to the abnormal sub-index. The specific value of the standard operation value can be determined according to the previous operation test data corresponding to the abnormal sub-index;

[0077] Monitor the real-time operation monitoring curve and the operation standard data range in the operation coordinate system. The operation standard data range includes the minimum value of the operation standard data and the maximum value of the operation standard data. Obtain all the areas enclosed by the real-time operation monitoring curve outside the operation standard data range, that is, the areas formed by the parts of the real-time operation monitoring curve exceeding the minimum value of the operation standard data and the maximum value of the operation standard data and enclosing them. Sum all the areas and set it as the monitoring anomaly value. If the monitoring anomaly value is 0, generate a normal verification analysis state and prompt, and at the same time re-mark the abnormal sub-index as a normal sub-index and do not perform multi-dimensional integration analysis of the abnormal impact;

[0078] If the monitoring anomaly value is not 0, then through the formula calculate to obtain the abnormal verification value YH corresponding to the abnormal sub-index; in the formula, JY is the monitoring anomaly value; T is the time difference between the start of the verification analysis of the abnormal sub-index and the acquisition of the last monitoring area, with the unit of seconds; BB is the monitoring anomaly standard value corresponding to the abnormal sub-index, which can be determined according to the design parameters of the coal mill or according to the previous test data of the coal mill;

[0079] It should be noted that the abnormal verification value is used to integrate and calculate different abnormal verification data corresponding to abnormal sub-indicators, so as to digitally represent the verification analysis status corresponding to the affiliated abnormal sub-indicators;

[0080] If the abnormal verification value is less than or equal to 1, a mild abnormal state of verification analysis is generated and prompted, and at the same time, the affiliated abnormal sub-indicator is re-marked as a mild abnormal sub-indicator of verification;

[0081] If the abnormal verification value is greater than 1, a severe abnormal state of verification analysis is generated and prompted, and at the same time, the affiliated abnormal sub-indicator is re-marked as a severe abnormal sub-indicator of verification;

[0082] In the embodiment of the present invention, by performing effective abnormal verification analysis on the monitoring and processing data of the fault indicators during the operation of the coal mill, the influence of false alarm data can be reduced, and at the same time, reliable verification analysis data support can be provided for the subsequent analysis of abnormal influences during the operation of the coal mill, which can effectively improve the reliability of subsequent abnormal supervision and treatment of the hydraulic oil particle size of the coal mill.

[0083] When integrating and analyzing the abnormal influences during the operation of the coal mill according to the effectively abnormal verification analysis data, the mild abnormal sub-indicators and severe abnormal sub-indicators of verification analysis in the verification analysis data are passed through the formula to calculate and obtain the influence integration value YZ; where i is different mild abnormal sub-indicators and severe abnormal sub-indicators of verification analysis, i = 1, 2, 3,..., n; n is a positive integer, which is the total number of all mild abnormal sub-indicators and severe abnormal sub-indicators of verification analysis; JHi is the abnormal verification value corresponding to different mild abnormal sub-indicators and severe abnormal sub-indicators of verification analysis; ai is the index influence coefficient corresponding to different mild abnormal sub-indicators and severe abnormal sub-indicators of verification analysis, which can be preset according to the operation influences corresponding to different abnormal sub-indicators, and the specific value of the index influence coefficient can be determined by professional technical personnel in this field according to work experience, or can also be determined according to the number of negative influences historically corresponding to the affiliated abnormal sub-indicators; YB is the influence integration standard value, which can be determined according to the design parameters of the coal mill, or can also be determined according to the previous test data of the coal mill;

[0084] It should be noted that the influence integration value is used to integrate and calculate all verification analysis data, so as to digitally represent the influence integration status corresponding to all abnormal sub-indicators;

[0085] If the influence integration value is empty, a normal state of influence integration is generated;

[0086] If the influence integration value is less than or equal to 1, a mild abnormal state of influence integration is generated;

[0087] If the influence integration value is greater than 1, a severe abnormal state of influence integration is generated;

[0088] Sort and combine the processed and obtained impact integration value with the analyzed and obtained normal impact integration state, mild abnormal impact integration state, or severe abnormal impact integration state to obtain the first impact integration processing data;

[0089] It can be understood that the first impact integration processing data is used for data integration calculation and analysis from the level of abnormal verification values;

[0090] In addition, count the total number of mild abnormal sub-indicators and the total number of severe abnormal sub-indicators in the verification analysis data respectively, and mark them as the first abnormal total and the second abnormal total. Then, perform data analysis on the first abnormal total and the second abnormal total through the abnormal integration recognition model, and output the corresponding impact integration state value ZZ;

[0091] Among them, the expression of the abnormal integration recognition model is In the formula, N1 and N2 are the first abnormal total and the second abnormal total respectively; N11 and N22 are the standard values of the first abnormal total and the second abnormal total respectively;

[0092] The impact integration state value includes numerical values of 0, 1, or 2;

[0093] Generate the normal impact integration state according to the impact integration state value with a numerical value of 0;

[0094] Generate the mild abnormal impact integration state according to the impact integration state value with a numerical value of 1;

[0095] Generate the severe abnormal impact integration state according to the impact integration state value with a numerical value of 2;

[0096] Sort and combine the processed and obtained impact integration state value with the analyzed and obtained normal impact integration state, mild abnormal impact integration state, or severe abnormal impact integration state to obtain the second impact integration processing data;

[0097] It can be understood that the second impact integration processing data is used for data integration calculation and analysis from the level of the results of the previous verification analysis; compared with the existing technical solutions that only perform data calculation analysis and management through a single level, there are large data errors and data reliability problems. The embodiments of the present invention can effectively improve the diversity and reliability of the abnormal impact processing analysis during the operation of the coal mill;

[0098] In addition, in the embodiments of the present invention, through the abnormal and effective verification analysis of the fault index monitoring processing data during the operation of the coal mill and the multi-dimensional integration analysis of abnormal impacts, the diverse and comprehensive abnormal data supervision processing and analysis of the operation of the coal mill are realized, and the multi-level supervision analysis effect of the abnormal hydraulic oil particle size during the operation of the coal mill is improved.

[0099] The device operation fault monitoring and evaluation management module is used to determine the abnormal state of the hydraulic oil particle size according to the first influence integrated processing data and the second influence integrated processing data obtained from the multi-dimensional integrated analysis during the operation of the coal mill, and implement targeted risk prevention management according to the abnormal state of the hydraulic oil particle size; it includes:

[0100] Traverse and analyze the first influence integrated processing data and the second influence integrated processing data obtained through processing;

[0101] If the influence integrated severe abnormal state does not exist simultaneously in the traversal results, implement the targeted first risk prevention management plan;

[0102] Otherwise, implement the targeted second risk prevention management plan;

[0103] Among them, the second risk prevention management plan is used to conduct overall detection and processing on the hydraulic oil and all fault sub-indicators, and the first risk prevention management plan is used to conduct local detection and processing on the hydraulic oil and abnormal fault sub-indicators.

[0104] In the embodiments of the present invention, the abnormal state of the hydraulic oil particle size is determined according to the first influence integrated processing data and the second influence integrated processing data obtained from the multi-dimensional integrated analysis during the operation of the coal mill, and targeted risk prevention management is implemented according to the abnormal state of the hydraulic oil particle size, realizing multi-dimensional supervision and processing management actively in the early stage when the hydraulic oil particle size is abnormal and has an impact, and improving the autonomous supervision and processing effect of the abnormal hydraulic oil particle size during the operation of the coal mill.

[0105] In addition, the formulas involved above are all calculated by removing the dimension and taking their numerical values, and are obtained by a software through simulating a large amount of data to get a formula that is closest to the actual situation.

[0106] In several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described invention embodiments are merely illustrative. For example, the division of modules is only a logical function division, and there can be other division methods in actual implementation.

[0107] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules. They can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] In addition, in each embodiment of the present invention, each functional module can be integrated into a processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above integrated module can be implemented in the form of hardware, or in the form of a combination of hardware and software functional modules.

[0109] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and without departing from the basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent monitoring system for coal mill operation failure based on artificial intelligence, characterized in that: It includes a multi-dimensional monitoring data processing module for equipment operation, which is used to monitor and collect data of different fault secondary indicators and fault main indicators during coal mill operation, and process and combine the monitoring and statistical data corresponding to different fault secondary indicators and fault main indicators to obtain fault indicator monitoring processing data; The equipment operation multi-dimensional processing data analysis module is used to perform abnormal effective verification analysis and multi-dimensional integration analysis of abnormal impact on the fault indicator monitoring and processing data during coal mill operation, and obtain the first impact integration processing data and the second impact integration processing data corresponding to the fault indicator monitoring and processing data; Among them, the fault indicator monitoring and processing data of the coal mill during operation is traversed and analyzed. If there is no element with a value of 1, a local normal operation state is generated and prompted; If the first element value is 1, a granularity exception is generated and a prompt is given; If there are elements whose values ​​are not 1, the abnormal sub-indicators corresponding to the elements whose values ​​are 1 are subjected to abnormal and effective verification analysis, and the real-time operation monitoring data corresponding to the abnormal sub-indicators are obtained. The real-time operation monitoring data are displayed and connected through the preset operation coordinate system to obtain the real-time operation monitoring curve corresponding to the abnormal sub-indicators. Monitor the real-time operation monitoring curve and the operation standard data range in the operation coordinate system, obtain the monitoring abnormal value of the real-time operation monitoring curve outside the operation standard data range, and if the monitoring abnormal value is 0, generate a verification analysis normal state and prompt, and at the same time re-mark the abnormal sub-indicator as a normal sub-indicator and do not perform multi-dimensional integrated analysis of the abnormal impact; If the monitored abnormal value is not 0, a multi-dimensional integrated analysis of the abnormal impact is performed to obtain the first impact integrated processing data and the second impact integrated processing data corresponding to the integrated analysis of different dimensions; The equipment operation fault monitoring and evaluation management module is used to determine the abnormal state of the hydraulic oil particle size based on the first impact integrated processing data and the second impact integrated processing data of the multi-dimensional integrated analysis during the operation of the coal mill, and implement targeted risk prevention management based on the abnormal state of the hydraulic oil particle size.

2. The intelligent monitoring system for coal mill operation failure based on artificial intelligence according to claim 1 is characterized in that: The operation of the coal mill is monitored and data is collected according to a number of preset fault sub-indicators. When processing and analyzing the single monitoring statistical states corresponding to a number of fault sub-indicators, the monitoring statistical data corresponding to different fault sub-indicators are analyzed in turn through the sub-indicator identification model, and the corresponding sub-indicator state value FZj is output; Among them, the expression of the secondary indicator identification model is: Wherein, j is a different fault secondary index, j = 1, 2, 3, ..., m; m is a positive integer; FSj is the monitoring statistical data corresponding to different fault secondary indexes; Uj is the operating standard data range corresponding to different fault secondary indexes; According to the secondary indicator status value of 0, the corresponding secondary indicator is marked as a normal secondary indicator; According to the secondary indicator status value of 1, the corresponding secondary indicator is marked as an abnormal secondary indicator.

3. The intelligent monitoring system for coal mill operation failure based on artificial intelligence according to claim 2 is characterized in that: Obtain monitoring statistics corresponding to the main fault indicators and compare them with the preset fault standard thresholds; If the value in the monitoring statistics is less than the fault standard threshold, the monitoring flag corresponding to the main fault indicator is set to 0; Otherwise, the monitoring flag corresponding to the main fault indicator is set to 1; The monitoring identifier corresponding to the main fault indicator and the secondary indicator state values ​​corresponding to different secondary fault indicators are sorted and combined to obtain the fault indicator monitoring processing data.

4. The intelligent monitoring system for coal mill operation failure based on artificial intelligence according to claim 3 is characterized in that: When conducting multi-dimensional integrated analysis of abnormal impact, the formula Calculate and obtain the abnormal verification value YH corresponding to the abnormal secondary indicator; where JY is the monitoring abnormal value; T is the time difference between the start of the verification analysis of the abnormal secondary indicator and the acquisition of the last monitoring area; BB is the monitoring abnormal standard value corresponding to the abnormal secondary indicator; If the abnormal verification value is less than or equal to 1, a verification analysis mild abnormal status is generated and prompted, and the corresponding abnormal sub-indicator is re-marked as a verification mild abnormal sub-indicator; If the abnormal verification value is greater than 1, a severe abnormal status of the verification analysis will be generated and prompted, and the corresponding abnormal sub-indicator will be re-marked as a severe abnormal sub-indicator of verification.

5. The intelligent monitoring system for coal mill operation failure based on artificial intelligence according to claim 4 is characterized in that: When conducting integrated analysis on the abnormal impact of coal mill operation based on abnormal effective verification analysis data, the verification minor abnormal sub-indicator and verification severe abnormal sub-indicator in the verification analysis data are combined by formula Calculate and obtain the impact integration value YZ; where i is different verification of mild abnormal sub-indicators and verification of severe abnormal sub-indicators, i=1, 2, 3,..., n; n is a positive integer; JHi is the abnormal verification value corresponding to different verification of mild abnormal sub-indicators and verification of severe abnormal sub-indicators; ai is the indicator influence coefficient corresponding to different verification of mild abnormal sub-indicators and verification of severe abnormal sub-indicators; YB is the impact integration standard value.

6. The intelligent monitoring system for coal mill operation failure based on artificial intelligence according to claim 5 is characterized in that: If the impact integration value is empty, the impact integration normal state is generated; If the impact integration value is less than or equal to 1, a slight abnormal state of impact integration is generated; If the impact integration value is greater than 1, a severe abnormal state of impact integration is generated; The impact integration value obtained by processing and the impact integration normal state, the impact integration slightly abnormal state or the impact integration seriously abnormal state obtained by analysis are sorted and combined to obtain first impact integration processing data.

7. The intelligent monitoring system for coal mill operation failure based on artificial intelligence according to claim 6 is characterized in that: The total number of minor abnormal sub-indicators and the total number of major abnormal sub-indicators in the verification analysis data are counted and marked as the first abnormal total number and the second abnormal total number respectively, and the first abnormal total number and the second abnormal total number are analyzed by the abnormal integration recognition model to output the corresponding impact integration state value ZZ; Among them, the expression of the abnormal integration recognition model is: Where N1 and N2 are the total number of the first anomaly and the total number of the second anomaly respectively; N11 and N22 are the standard value of the total number of the first anomaly and the standard value of the total number of the second anomaly respectively; The value affecting the integration status contains a value of 0, 1, or 2.

8. The intelligent monitoring system for coal mill operation failure based on artificial intelligence according to claim 7 is characterized in that: Generate an impact integration normal state according to the impact integration state value having a value of 0; Generate an impact integration mild abnormal state according to the impact integration state value of 1; Generate an impact integration severe abnormal state according to the impact integration state value of 2; The impact integration state value obtained through processing and the impact integration normal state, the impact integration slightly abnormal state or the impact integration seriously abnormal state obtained through analysis are sorted and combined to obtain second impact integration processing data.

9. The intelligent monitoring system for coal mill operation failure based on artificial intelligence according to claim 8 is characterized in that: Performing traversal analysis on the first impact integration processing data and the second impact integration processing data obtained by processing; If there are no severe abnormal states that affect integration in the traversal results, the targeted first risk prevention management plan will be implemented; Otherwise, a targeted second risk prevention and management plan will be implemented.

10. The intelligent monitoring system for coal mill operation failure based on artificial intelligence according to claim 1, characterized in that: Obtain all areas enclosed by the real-time operation monitoring curve outside the operation standard data range, sum all areas and set them as monitoring abnormal values.

Images