WO2022252424A1

WO2022252424A1 - Intelligent detection method and system for pulverizer screening piece

Info

Publication number: WO2022252424A1
Application number: PCT/CN2021/116929
Authority: WO
Inventors: 范文海; 唐军; 周辉; 韩动梁; 倪鹏
Original assignee: 江苏邦鼎科技有限公司
Priority date: 2021-05-31
Filing date: 2021-09-07
Publication date: 2022-12-08
Also published as: CN113275118B; CN113275118A

Abstract

An intelligent detection method and system for a pulverizer screening piece, the method comprising: performing edge detection on first image information to obtain first granularity information (S200); determining whether the first granularity information is in a first preset dynamic granularity threshold, and using an obtained first determination result as first interlocking information (S300, S400); performing current monitoring on a first pulverizer to obtain first current monitoring information (S500); determining, according to the first current monitoring information, whether a first screen is in a damaged state, and using an obtained second determination result as second interlocking information (S600, S700); inputting the first interlocking information and the second interlocking information into a first interlocking logic rule for determination, so as to obtain a third determination result (S800); and obtaining a first interlocking instruction according to the third determination result (S900). The method and the system solves the technical problem in the existing technology that monitoring of the working state of a screening piece is not intelligent enough, thereby affecting the efficiency of material screening.

Description

A method and system for intelligent detection of pulverizer sieve

technical field

The invention relates to the related field of pulverizer detection, in particular to an intelligent detection method and system for a pulverizer screen.

Background technique

The pulverizer is a machine that uses mechanical methods to overcome the internal cohesion of solid materials and split them. It is widely used because of its simple structure, strong versatility, high production efficiency, and convenient use and maintenance. Since the reliability of the pulverizer operation directly affects the production efficiency and the normal operation of the subsequent processes, among them, the screen, as the main discharge equipment, directly contacts with the screened materials, which directly affects the screening efficiency of the pulverizer. It is particularly important to eliminate mechanical failures in a short period of time and resume production as soon as possible.

However, in the process of realizing the technical solution of the invention in the embodiment of the present application, the inventor of the present application found that the above-mentioned technology has at least the following technical problems:

In the prior art, there is a technical problem that the monitoring of the working state of the sieve is not intelligent enough due to the structure and process of the sieve itself, thereby affecting the screening efficiency of materials.

Contents of the invention

The embodiment of the present application provides an intelligent detection method and system for the sieve of a pulverizer, which solves the problem in the prior art that due to the structure and process of the sieve, the monitoring of the working state of the sieve is not intelligent enough, which affects the The technical problem of material screening efficiency has achieved the technical effect of intelligent fault detection and timely early warning by means of edge detection on the screen material and current monitoring data analysis.

In view of the above problems, it is proposed that an embodiment of the present application provides an intelligent detection method and system for a pulverizer screen.

In the first aspect, an embodiment of the present application provides an intelligent detection method for a pulverizer screen, wherein the method is applied to an intelligent detection system for a pulverizer screen, and the system is intelligently connected to a camera, and the method includes : According to the first camera, obtain the first image information of the oversize of the first pulverizer; by performing edge detection on the first image information, obtain the first granularity information; judge whether the first granularity information is in the first preset Set the dynamic granularity threshold to obtain the first judgment result; use the first judgment result as the first interlock information; obtain the first current monitoring information by monitoring the current of the first pulverizer; according to the first current The monitoring information judges whether the first screen is in a damaged state, and obtains a second judgment result, wherein the oversize of the first pulverizer is on the first screen; the second judgment result is used as the second interactive lock information; input the first interlock information and the second interlock information into a first interlock logic rule for judgment, and obtain a third judgment result; according to the third judgment result, obtain a first interlock instruction; The first shredder is interlocked according to the first interlock instruction.

On the other hand, the present application also provides an intelligent detection system for a pulverizer sieve, the system includes: a first obtaining unit, the first obtaining unit is used to obtain the oversize of the first pulverizer according to the first camera the first image information; the second obtaining unit, the second obtaining unit is used to obtain the first granularity information by performing edge detection on the first image information; the first judging unit, the first judging unit is used for Judging whether the first granularity information is at a first preset dynamic granularity threshold, and obtaining a first judgment result; a first operation unit, the first operation unit is used to use the first judgment result as the first interlocking information; A third obtaining unit, the third obtaining unit is used to obtain the first current monitoring information by performing current monitoring on the first pulverizer; a second judging unit, the second judging unit is used to obtain the first current monitoring information according to the first The current monitoring information judges whether the first screen is in a damaged state, and obtains a second judgment result, wherein, the oversize of the first pulverizer is on the first screen; the second operation unit, the second operation The unit is used to use the second judgment result as the second interlock information; the first input unit is used to input the first interlock information and the second interlock information into the first interlock information. The lock logic rule judges to obtain the third judgment result; the fourth obtaining unit is used to obtain the first interlock instruction according to the third judgment result; the first interlock unit, the first The interlock unit is used for interlocking the first shredder according to the first interlock instruction.

In a third aspect, the present invention provides an intelligent detection system for a pulverizer sieve, including a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein, when the processor executes the program, The steps of the method described in the first aspect are realized.

One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

Since the first camera is used to obtain the image information of the annular material on the screen of the first pulverizer, then the calculation and analysis of edge detection is performed on the image information to obtain the material particle size information of the material ring, and it is judged whether the first particle size information is in the A first preset dynamic particle size threshold, wherein the first preset dynamic particle size threshold is determined based on crushed materials and sieve holes, and a first judgment result is obtained. Further, by monitoring the current of the screen of the first pulverizer, and judging the damage state of the screen according to the current monitoring information, a second judgment result is obtained, and then the first judgment result and the second judgment result As the corresponding first interlock information and second interlock information, enter the interlock logic rule for judgment, and send an interlock signal to the main control system to complete the power supply interlock according to the judgment result. The method of edge detection and current monitoring data analysis realizes the technical effect of intelligent fault detection and timely early warning.

The above description is only an overview of the technical solution of the present application. In order to better understand the technical means of the present application, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present application more obvious and understandable , the following specifically cites the specific implementation manner of the present application.

Description of drawings

Fig. 1 is a schematic flow chart of an intelligent detection method for a pulverizer sieve according to an embodiment of the present application;

FIG. 2 is a schematic structural diagram of an intelligent detection system for a pulverizer screen according to an embodiment of the present application;

Fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.

Description of reference numerals: first obtaining unit 11 , second obtaining unit 12 , first judging unit 13 , first operating unit 14 , third obtaining unit 15 , second judging unit 16 , second operating unit 17 , first input Unit 18 , fourth obtaining unit 19 , first interlocking unit 20 , computing device 300 , memory 310 , processor 320 , and input/output interface 330 .

Detailed ways

The embodiment of the present application provides an intelligent detection method and system for the sieve of a pulverizer, which solves the problem in the prior art that due to the structure and process of the sieve, the monitoring of the working state of the sieve is not intelligent enough, which affects the The technical problem of material screening efficiency has achieved the technical effect of intelligent fault detection and timely early warning by means of edge detection on the screen material and current monitoring data analysis. Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described here.

Application overview

The near pulverizer is a machine that uses mechanical methods to overcome the internal cohesion of solid materials and split them. It is widely used because of its simple structure, strong versatility, high production efficiency, and convenient use and maintenance. Since the reliability of the pulverizer operation directly affects the production efficiency and the normal operation of the subsequent processes, among them, the screen, as the main discharge equipment, directly contacts with the screened materials, which directly affects the screening efficiency of the pulverizer. It is particularly important to eliminate mechanical failures in a short period of time and resume production as soon as possible. However, there are technical problems in the prior art that the monitoring of the working state of the sieve is not intelligent enough due to the structure and process of the sieve itself, thereby affecting the screening efficiency of materials.

In view of the above technical problems, the general idea of the technical solution provided by this application is as follows:

An embodiment of the present application provides an intelligent detection method for a pulverizer screen, wherein the method is applied to an intelligent detection system for a pulverizer screen, and the system is intelligently connected to a camera. The method includes: according to the first The camera is used to obtain the first image information of the oversize of the first pulverizer; to obtain the first granularity information by performing edge detection on the first image information; to determine whether the first granularity information is at the first preset dynamic granularity threshold , obtain the first judgment result; use the first judgment result as the first interlocking information; obtain the first current monitoring information by monitoring the current of the first pulverizer; judge the first current monitoring information according to the first current monitoring information Whether a screen is in a damaged state, obtain a second judgment result, wherein the oversize of the first pulverizer is on the first screen; use the second judgment result as the second interlocking information; The first interlock information and the second interlock information are input into a first interlock logic rule for judgment, and a third judgment result is obtained; according to the third judgment result, a first interlock instruction is obtained; according to the first interlock instruction An interlock command interlocks the first shredder.

After introducing the basic principles of the present application, the embodiments of the present application will be described below in conjunction with the accompanying drawings. Those of ordinary skill in the art know that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

Embodiment one

As shown in Figure 1, an embodiment of the present application provides an intelligent detection method for a pulverizer screen, wherein the method is applied to an intelligent detection system for a pulverizer screen, the system is intelligently connected to a camera, and the Methods include:

Step S100: According to the first camera, obtain the first image information of the oversize of the first pulverizer;

Specifically, the first camera is a miniature camera, and the first camera is assembled in the unit space of the pulverizer, and then collects images of the materials on the screen of the pulverizer, wherein, due to the operation of the pulverizer The state will cause the material to perform circular motions such as crushing, grinding, etc., and the centrifugal force will cause the material to fall off and form a material ring on the side of the sieve. Therefore, the acquisition of the first image information can clearly and clearly understand that it is in The quality and stratification of the materials on the sieve in the pulverizer are convenient for further analysis and processing.

Step S200: Obtain first granularity information by performing edge detection on the first image information;

Specifically, the edge detection is a basic problem in image processing and computer vision. The purpose of edge detection is to identify points in the first image information where the material on the sieve side changes significantly, such as the edge of the material. Further, In the process of edge detection, image preprocessing is performed on the image and then edge detection is further performed, and the obtained first particle size information is compared with the sieve hole of the first pulverizer to form a rule judgment. Among them, the shape of the sieve mesh is mostly geometric and changes based on the crushed material, so as to obtain comparative parameters for further analysis. Among them, because the significant changes in the image properties will reflect the important changes, generally speaking, the quality of the coarse and fine materials is different, resulting in the layering of the material ring, the layer of coarse material is close to the side of the sieve, and the layer of fine material is covered by the coarse material. on the granular layer. If the circulation layer of the material cannot be destroyed, it will not only affect the return of the large particle material to the crushing area, but also affect the sieving of the fine material. Therefore, by further determining the particle size information of the material and detecting the material on the sieve, it can be checked in time. The hidden danger of material accumulation reduces the failure of the pulverizer.

Step S300: judging whether the first granularity information is within a first preset dynamic granularity threshold, and obtaining a first judging result;

Step S400: using the first judgment result as the first interlocking information;

Specifically, the process of judging whether the first granularity information is within the first preset dynamic granularity threshold is a judgment based on a logical judgment model, wherein the first preset dynamic granularity threshold is based on the purpose of the sieve. The number and the service life of the sieve are determined, so as to ensure that the material can be screened through the sieve holes, and the setting of the dynamic threshold is to adapt to the change characteristics of the material quality on the sieve, and then complete the screening of the sieve material ring. The further judgment is to judge whether the first granularity information is within the first preset dynamic granularity threshold, if the first granularity information is not within the first preset dynamic granularity threshold, it means that the material loop The particle size is relatively large, and the corresponding sieving cannot be completed through the friction on the sieve; The first judgment result is used as the first interlocking information to analyze the interlocking rules.

Step S500: Obtain first current monitoring information by performing current monitoring on the first pulverizer;

Specifically, the current monitoring of the first pulverizer is to monitor and analyze the current data of the screen in the pulverizer in detail, wherein the screen will be heat-treated during the assembly process to ensure During the material screening process, the heat generated by the friction of the sieve will not damage the mesh of the sieve in a large area. Among them, welding with a small current is also used in the manufacturing process of the sieve. Therefore, through the first pulverizer The current of the screen is monitored, and the current monitoring information is correspondingly obtained, wherein the first current monitoring information can generate a monitoring curve to complete multiple comparisons and analyzes to determine the use status of the screen.

Step S600: Judging whether the first screen is in a damaged state according to the first current monitoring information, and obtaining a second judgment result, wherein the oversize of the first pulverizer is on the first screen;

Step S700: using the second judgment result as the second interlocking information;

Specifically, according to the first current monitoring information, it is further judged whether the first screen is in a damaged state, and the state of this judgment is also judged by a logical judgment model, and the corresponding model is called when the judgment is made, wherein In the process of judging and comparing, specific settings are made based on the historical first current monitoring information and the set current threshold, so as to determine the current normal characteristics. When the first current monitoring information conforms to the current normal characteristics, it means that the current first current monitoring information A screen is in an undamaged state, and when the first current monitoring information does not conform to the current normal feature, it means that the second screen is currently in a damaged state, that is, the second judgment result also includes two logical judgment results, and using the second judgment result as the second interlocking information to analyze the interlocking rules.

Step S800: Input the first interlock information and the second interlock information into a first interlock logic rule for judgment, and obtain a third judgment result;

Specifically, the first interlock logic rule is constructed based on the logic state, and the constructed logic judgment rule is analyzed concretely with the first interlock information and the second interlock information, wherein , the interlocking rules can ensure the safe use of the first pulverizer and eliminate potential safety hazards. Further, the interlocking control is mainly to ensure the safe use of the pulverizer, analyze the situation of failure specifically, and obtain the third judgment result, wherein the third judgment result includes four state results , the first state, the second state, the third state and the fourth state, wherein the interlock condition is satisfied when the third judgment result is the first state, and not satisfied when the third judgment result is not the first state The detailed early warning analysis process of interlocking conditions has achieved the technical effect of detailed early warning analysis for fault conditions.

Step S900: Obtain a first interlock instruction according to the third judgment result;

Step S1000: Interlock the first shredder according to the first interlock instruction.

Specifically, when the third judgment result is in the first state, according to the first interlock instruction, the main control system of the first pulverizer is controlled by switch interlock, so as to improve the operational safety of the pulverizer, and The first pulverizer intelligently detects the sieve when it is in use, and achieves the method of interlocking logic judgment by generating interlocking information through edge detection on the sieve and current monitoring data analysis, and realizing intelligent fault detection The technical effect of timely warning.

Furthermore, the system is also intelligently connected to a vibrating device, wherein the vibrating device also includes a detection unit and a vibrating unit, step S200 in this embodiment of the present application further includes:

Step S210: obtaining a second preset dynamic granularity threshold;

Step S220: If the first granularity information is not within the first preset dynamic granularity threshold, determine whether the first granularity information is within the second preset dynamic granularity threshold;

Step S230: If the first granularity information is within the second preset dynamic granularity threshold, according to the detection unit, obtain first real-time vibration data;

Step S240: Obtain second real-time vibration data according to the first real-time vibration data and the second preset dynamic granularity threshold, wherein the first real-time vibration data is smaller than the second real-time vibration data;

Step S250: Obtain a first vibration instruction according to the vibration unit;

Step S260: Vibrating the first screen according to the first vibration instruction according to the second real-time vibration data.

Specifically, the second preset dynamic threshold is different from the first preset dynamic threshold, and the second preset dynamic threshold is smaller than the first preset dynamic threshold, when the first granularity information When it is not at the first preset dynamic particle size threshold, it means that the first particle size is relatively large and cannot meet the requirements of the sieve mesh for sieving, and then the first pulverizer is connected to the vibration unit and the detection unit. Vibration detection, because the first pulverizer will generate some vibrations when it enters the working state, so that it is convenient for the equipment to rub against the sieve and sieve the corresponding materials to improve the screening efficiency. Therefore, by increasing the first The vibration device completes the vibration detection and improves its vibration data to facilitate the vibration of the ring-shaped material layer on the sieve to promote the full screening of materials, so as to achieve accurate detection and setting based on the vibration device, and improve the screening efficiency and screening quality. Effect.

Furthermore, where the second real-time vibration data is obtained according to the first real-time vibration data and the second preset dynamic granularity threshold, step S240 in this embodiment of the present application further includes:

Step S241: Obtain the first pulverized material information of the first pulverizer;

Step S242: Obtain first hardness information according to the first pulverized material information;

Step S243: Obtain first roughness information according to the first image information, wherein the first roughness information is the surface roughness of the oversize;

Step S244: perform vibration prediction according to the first hardness information and the first roughness information, and obtain first predicted vibration data;

Step S245: Use the first predicted vibration data as the second real-time vibration data.

Specifically, the first pulverized material information is the material attribute information pulverized by the first pulverizer during material pulverization, such as the characteristics of the material, the hardness of the material, etc. Further, since the material is from The upper feeding port enters, and the direction of the material movement vector is downward to complete the further pulverization process of the material. The particle composition in the inner cavity of the pulverizer will also change. To determine the appropriate screening parameters for a certain raw material and a certain sieve hole, such as sieve hole selection , catalytic selection, etc. Furthermore, according to the obtained material hardness and the surface roughness of the material in the sieve material layer, it will affect the subsequent screening efficiency. Therefore, according to the first hardness information and the first roughness information, it is input into the vibration data prediction model Among them, the vibration data prediction model is a model constructed by concrete logic induction through multiple sets of sample data, wherein, before the model is used, the model will be updated based on the newly added samples to achieve the accuracy of the output data, and then Using the obtained first predicted vibration data as the second real-time vibration data to vibrate the sieve in the first pulverizer, thereby improving the screening efficiency of the sieve.

Further, the incremental learning of the first noise prediction training model according to the first road surface noise reduction index to obtain a second noise prediction training model, the step S240 of the embodiment of the present application further includes:

Step S246: Obtain the first structure production information of the first pulverizer;

Step S247: Create information according to the first structure to obtain a first spatial distance;

Step S248: Obtain a first vibration amplitude according to the first spatial distance;

Step S249: Constrain the first vibration amplitude as a first constraint condition of the second real-time vibration data.

Specifically, the first structure production information is the inner cavity manufacturing process information of the first pulverizer, including the main functions of the pulverizer and the equipment needed in its pulverization process, so as to determine the relationship between the first sieve and the For the spatial distance between the instruments in the previous process, the obtained first spatial distance is used as the constraint condition of the upper limit of the safety distance. Further, the vibration amplitude results in multiple sets of training data of the vibration prediction model are obtained, and all The largest data in the result is used as a constraint condition, thereby completing the effective distance constraint condition according to its vibration replication and spatial distance, and further constraining the second real-time vibration data, wherein, because the second real-time vibration data is greater than the real-time The detected first real-time vibration data passes the first constraint condition, so that the second real-time vibration data is smaller than the corresponding data of the first constraint condition, thereby ensuring that the vibration data will not be increased while The material collides with the previous equipment for crushing the material, which achieves the technical effect of improving the crushing efficiency of the pulverizer and ensuring the safety of use.

Further, step S241 in this embodiment of the present application also includes:

Step S2411: Obtain a first working environment of the first shredder, wherein the first working environment includes an external environment and an internal environment;

Step S2412: Obtain first temperature information and first humidity information according to the first working environment;

Step S2413: Obtain a first environmental characteristic according to the first temperature information and the first humidity information;

Step S2414: Obtain a first attribute feature according to the first pulverized material, wherein the first attribute feature includes a material high temperature feature and a material humidity feature;

Step S2415: Generate a first impact index according to the first environmental feature and the first attribute feature;

Step S2416: Obtain a first early warning signal according to the first impact index.

Specifically, through data detection of the internal environment and external environment of the first pulverizer in the working state, the temperature change characteristics and humidity change characteristics are determined according to the detected data, and the corresponding change characteristics are applied to the corresponding Environmental characteristics, further, according to the information of the first pulverized material, the reaction characteristics of the material in the high and low temperature state, as well as the reaction characteristics in the dry environment and the humidity environment are obtained. Because different materials may have different effects when crushed, for example, when the humidity in the environment is high and the materials are easily bonded when crushed, the materials before screening will agglomerate, which will affect the quality of screening. Therefore, it is necessary to Inputting the corresponding environmental characteristics and material attribute characteristics into the material impact training model for data characteristic information, wherein the data in the first environmental characteristics and the first attribute characteristics are multiple sets of standard data calculated based on multiple data, The data that can reflect the specific level of characteristics, and then judge according to the first impact index output by the material impact training model. When the first impact index is too large, it is necessary to obtain an early warning signal to provide an early warning reminder, achieving intelligent The technical effect of automated fault detection and timely early warning.

Further, the obtaining of the first interlock instruction according to the third judgment result, S900 in this embodiment of the present application further includes:

Step S910: If the first interlock information and the second interlock information do not meet the predetermined requirement in the third judgment result, obtain the first interlock instruction, wherein the predetermined requirement is logic The "yes" state in the judgment state;

Step S920: If the first interlocking information meets the predetermined requirement in the third judgment result, and the second interlocking information does not meet the predetermined requirement, obtain a first speed regulation instruction, wherein the The first speed regulation command is used to adjust the speed of the first pulverizer;

Step S930: If the first interlocking information does not meet the predetermined requirement in the third judgment result, and the second interlocking information meets the predetermined requirement, obtain a first maintenance instruction, wherein the The first maintenance instruction is used to perform maintenance on the first screen.

Specifically, the predetermined requirement is a "yes" state in the logical judgment state, and in detail, the predetermined requirement is a result of the first judgment result that is not within the first dynamic preset granularity threshold. The result in the damaged state in the second judgment result. The other result of the first judgment result and the second judgment result is "not" state, that is, it does not meet the predetermined requirements, thereby forming a judgment analysis of logic rules, further, for the first interlock When the information and the second interlocking information meet the predetermined requirements at the same time, the system is controlled. When the first interlocking information is satisfied and the second interlocking information is not satisfied, it means that the screen is not damaged but the material is layered. It affects the screening efficiency. Therefore, it is necessary to adjust the material entry speed according to the first speed regulation command. When the first interlock information is not satisfied and the second interlock information is satisfied, it means that the screen is damaged and affects the screening efficiency. Therefore, it is necessary to overhaul the materials, achieving the technical effect of improving the screening efficiency and screening quality on the basis of ensuring the safe operation of the pulverizer.

Further, the generating of the first impact index according to the first environmental characteristics and the first attribute characteristics, step S2415 in this embodiment of the present application further includes:

Step S24151: using the first environmental feature and the first attribute feature as input information to construct a material impact training model;

Step S24152: The material impact training model is obtained by training multiple sets of training data until convergence, wherein each set of data in the multiple sets of training data includes the first environmental feature, the first attribute feature and the Identification information used to identify the first impact index;

Step S24153: Obtain an output result of the material impact training model, the output result including the first impact index.

Specifically, the first impact index is input into each set of training data as supervisory data for supervised learning, and the material influence training model is a model based on a neural network model, and a neural network is a large number of neural networks. It is an operation model formed by the interconnection of elements, and the output of the network is expressed according to a logical strategy of the connection mode of the network. Further, the training process is essentially a supervised learning process, and each of the multiple sets of training data includes the first environmental feature, the first attribute feature and the first impact index used to identify The identification information of the material affects the training model for continuous self-correction and adjustment until the obtained output results are consistent with the identification information, and the supervised learning of this group of data is ended, and the supervised learning of the next set of data is carried out. When the output information of the material impact training model reaches the predetermined accuracy rate/reaches the convergence state, the supervised learning process ends, and the training of the material impact training model is achieved so that the output of the first impact index is more accurate, reaching the data The technical effect of intelligent analysis.

Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general-purpose hardware, and of course it can also be realized by special hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, Special components, etc. to achieve. In general, all functions completed by computer programs can be easily realized by corresponding hardware, and the specific hardware structure used to realize the same function can also be varied, such as analog circuits, digital circuits or special-purpose circuit etc. However, for this application, software program implementation is a better implementation mode in most cases. Based on this understanding, the essence of the technical solution of this application or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a readable storage medium, such as a floppy disk of a computer , U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., including several instructions to make a computer device execute the method described in each embodiment of the present application.

To sum up, the intelligent detection method and system for the pulverizer screen provided by the embodiment of the present application have the following technical effects:

1. Since the image information of the annular material on the screen of the first pulverizer is obtained through the first camera, then the calculation and analysis of edge detection is performed on the image information to obtain the material particle size information of the material ring, and it is judged whether the first particle size information is in the The first preset dynamic particle size threshold, wherein the first preset dynamic particle size threshold is determined based on the pulverized material and the sieve hole, and the first judgment result is obtained. Further, by monitoring the current of the screen of the first pulverizer, and judging the damage state of the screen according to the current monitoring information, a second judgment result is obtained, and then the first judgment result and the second judgment result As the corresponding first interlock information and second interlock information, enter the interlock logic rule for judgment, and send an interlock signal to the main control system to complete the power supply interlock according to the judgment result. The method of edge detection and current monitoring data analysis realizes the technical effect of intelligent fault detection and timely early warning.

2. Due to the adoption of the method of completing vibration detection and improving its vibration data by adding the first vibration device, it is convenient to vibrate the ring-shaped material layer on the sieve and promote the sufficient screening of materials, thus achieving the vibration unit and detection based on The unit completes the accurate detection and setting of the sieve, and improves the technical effect of sieving efficiency and sieving quality.

3. Due to the specific analysis of each attribute of the material, the data processing and calculation method of intelligent early warning can be carried out according to the corresponding analysis results, and the screening efficiency can be improved on the basis of ensuring the safe operation of the pulverizer. and technical effects of sieving quality.

Embodiment two

Based on the same inventive concept as the intelligent detection method for the sieve of a pulverizer in the foregoing embodiments, the present invention also provides an intelligent detection system for a sieve of a pulverizer, as shown in FIG. 2 , the system includes:

A first obtaining unit 11, the first obtaining unit 11 is used to obtain the first image information of the oversize of the first pulverizer according to the first camera;

A second obtaining unit 12, configured to obtain first granularity information by performing edge detection on the first image information;

A first judging unit 13, the first judging unit 13 is configured to judge whether the first granularity information is within a first preset dynamic granularity threshold, and obtain a first judging result;

A first operation unit 14, configured to use the first judgment result as the first interlock information;

A third obtaining unit 15, the third obtaining unit 15 is configured to obtain first current monitoring information by performing current monitoring on the first shredder;

The second judging unit 16, the second judging unit 16 is used to judge whether the first screen is in a damaged state according to the first current monitoring information, and obtain a second judging result, wherein the first pulverizer oversize on said first screen;

A second operation unit 17, the second operation unit 17 is configured to use the second judgment result as the second interlock information;

A first input unit 18, configured to input the first interlock information and the second interlock information into a first interlock logic rule for judgment, and obtain a third judgment result;

A fourth obtaining unit 19, the fourth obtaining unit 19 is configured to obtain the first interlock instruction according to the third judgment result;

A first interlock unit 20, the first interlock unit 20 is used for interlocking the first shredder according to the first interlock instruction.

Further, the system also includes:

A fifth obtaining unit, the fifth obtaining unit is used to obtain a second preset dynamic granularity threshold;

A third judging unit, the third judging unit is configured to judge whether the first granularity information is in the second preset dynamic granularity if the first granularity information is not in the first preset dynamic granularity threshold threshold;

A sixth obtaining unit, the sixth obtaining unit is configured to obtain the first real-time vibration data according to the detection unit if the first granularity information is within the second preset dynamic granularity threshold;

A seventh obtaining unit, the seventh obtaining unit is configured to obtain second real-time vibration data according to the first real-time vibration data and the second preset dynamic granularity threshold, wherein the first real-time vibration data is smaller than the specified The second real-time vibration data;

An eighth obtaining unit, the eighth obtaining unit is used to obtain the first vibration instruction according to the vibration unit;

A first vibration unit, configured to vibrate the first screen according to the first vibration instruction according to the second real-time vibration data.

Further, the system also includes:

A ninth obtaining unit, the ninth obtaining unit is used to obtain the first crushed material information of the first grinder;

A tenth obtaining unit, the tenth obtaining unit is used to obtain first hardness information according to the first pulverized material information;

An eleventh obtaining unit, the eleventh obtaining unit is configured to obtain first roughness information according to the first image information, wherein the first roughness information is the surface roughness of the oversize;

A twelfth obtaining unit, the twelfth obtaining unit is configured to perform vibration prediction according to the first hardness information and the first roughness information, and obtain first predicted vibration data;

A third operating unit, the third operating unit is configured to use the first predicted vibration data as the second real-time vibration data.

Further, the system also includes:

A thirteenth obtaining unit, the thirteenth obtaining unit is used to obtain the first structure production information of the first pulverizer;

A fourteenth obtaining unit, the fourteenth obtaining unit is configured to produce information according to the first structure and obtain the first spatial distance;

A fifteenth obtaining unit, the fifteenth obtaining unit is configured to obtain a first vibration amplitude according to the first spatial distance;

A fourth operating unit, configured to constrain the first vibration amplitude as a first constraint condition of the second real-time vibration data.

Further, the system also includes:

A sixteenth obtaining unit, the sixteenth obtaining unit is used to obtain the first working environment of the first pulverizer, wherein the first working environment includes an external environment and an internal environment;

A seventeenth obtaining unit, the seventeenth obtaining unit is configured to obtain first temperature information and first humidity information according to the first working environment;

An eighteenth obtaining unit, the eighteenth obtaining unit is configured to obtain a first environmental characteristic according to the first temperature information and the first humidity information;

A nineteenth obtaining unit, the nineteenth obtaining unit is used to obtain a first attribute characteristic according to the first pulverized material, wherein the first attribute characteristic includes a material high temperature characteristic and a material humidity characteristic;

A first generating unit, configured to generate a first impact index according to the first environmental characteristics and the first attribute characteristics;

A twentieth obtaining unit, the twentieth obtaining unit is configured to obtain a first early warning signal according to the first impact index.

Further, the system also includes:

A twenty-first obtaining unit, the twenty-first obtaining unit is configured to obtain the The first interlock instruction, wherein the predetermined requirement is a "yes" state in the logic judgment state;

A twenty-second obtaining unit, the twenty-second obtaining unit is configured to if the first interlocking information meets the predetermined requirement in the third judgment result, and the second interlocking information does not meet the predetermined requirement Obtaining a first speed regulation instruction when a predetermined requirement is required, wherein the first speed regulation instruction is used to adjust the speed of the first pulverizer;

A twenty-third obtaining unit, the twenty-third obtaining unit is configured to: if the first interlocking information does not meet the predetermined requirement in the third judgment result, and the second interlocking information meets the When a predetermined requirement is required, a first maintenance instruction is obtained, wherein the first maintenance instruction is used to perform maintenance on the first screen.

Further, the system also includes:

A first construction unit, the first construction unit is used to construct a material impact training model by using the first environmental characteristics and the first attribute characteristics as input information;

The twenty-fourth obtaining unit, the twenty-fourth obtaining unit is used to obtain the material influence training model through multiple sets of training data training until convergence, wherein each set of data in the multiple sets of training data includes the The first environmental feature, the first attribute feature, and identification information used to identify the first impact index;

A twenty-fifth obtaining unit, the twenty-fifth obtaining unit is configured to obtain an output result of the material influence training model, and the output result includes the first influence index.

The embodiment of the present application can divide the functional modules of the network device and the terminal device according to the above method example, for example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one receiving module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules. It should be noted that the division of modules in the embodiment of the present application is schematic, and is only a logical function division, and there may be other division methods in actual implementation. Through the foregoing detailed description of an intelligent detection method for a pulverizer sieve, those skilled in the art can clearly know the implementation method of an intelligent detection system for a pulverizer sieve in this embodiment. More details.

exemplary electronic device

3 is a schematic diagram of a computing device of the present application. The computing device 300 shown in FIG. 3 may include: a memory 310, a processor 320, and an input/output interface 330. Wherein, the memory 33, the processor 320 and the input/output interface 330 are connected through an internal connection path, the memory 33 is used to store instructions, and the processor 320 is used to execute the instructions stored in the memory 320 to control the input/output interface 330 to receive Input data and information, output operation results and other data. .

FIG. 3 is a schematic diagram of a computing device according to another embodiment of the present application. The computing device 300 shown in FIG. 3 may include: a memory 310, a processor 320, and an input/output interface 330. Wherein, the memory 310, the processor 320 and the input/output interface 330 are connected through an internal connection path, the memory 310 is used to store instructions, and the processor 320 is used to execute the instructions stored in the memory 320 to control the input/output interface 330 to receive Input data and information, output operation results and other data.

In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware in the processor 320 or instructions in the form of software. The abnormal message identification method and/or the abnormal message identification model training method disclosed in the embodiments of the present application may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers, and the like. The storage medium is located in the memory 310, and the processor 320 reads the information in the memory 310, and completes the steps of the above method in combination with its hardware. To avoid repetition, no detailed description is given here.

It should be understood that, in the embodiment of the present application, the processor may be a central processing unit (central processing unit, CPU), and the processor may also be other general processors, digital signal processors (digital signal processor, DSP), application specific integrated circuits ( application specific integrated circuit (ASIC), off-the-shelf programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.

It should be understood that in the embodiment of the present application, the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the processor may also include non-volatile random access memory. For example, the processor may also store device type information.

It should be understood that, in various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, and should not be used in the embodiments of the present application. The implementation process constitutes any limitation.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.

In the above embodiments, all or part of them may be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application will be generated in whole or in part. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server or data center Transmission to another website site, computer, server or data center via wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be read by a computer, or a data storage device such as a server or a data center integrated with one or more available media. The available medium may be a magnetic medium, (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital versatile disc (Digital Video Disc, DVD)) or a semiconductor medium (for example, a solid state disk (Solid State Disk, SSD) )Wait.

The above is only a specific implementation of the application, but the scope of protection of the application is not limited thereto. Anyone familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the application. Should be covered within the protection scope of this application. Therefore, the protection scope of the present application should be determined by the protection scope of the claims.

Claims

An intelligent detection method for a pulverizer screen, wherein the method is applied to an intelligent detection system for a pulverizer screen, the system is intelligently connected to a camera, and the method includes:

According to the first camera, the first image information of the oversize of the first pulverizer is obtained;

Obtaining first granularity information by performing edge detection on the first image information;

judging whether the first granularity information is within a first preset dynamic granularity threshold, and obtaining a first judging result;

using the first judgment result as the first interlocking information;

Obtaining first current monitoring information by performing current monitoring on the first pulverizer;

Judging whether the first screen is in a damaged state according to the first current monitoring information, and obtaining a second judgment result, wherein the oversize of the first pulverizer is on the first screen;

using the second judgment result as the second interlocking information;

inputting the first interlocking information and the second interlocking information into a first interlocking logic rule for judgment, and obtaining a third judgment result;

Obtain a first interlock instruction according to the third judgment result;

The first shredder is interlocked according to the first interlock instruction.
The method according to claim 1, wherein the system is also intelligently connected with a vibrating device, wherein the vibrating device further comprises a detection unit and a vibrating unit, and the method further comprises:

obtaining a second preset dynamic granularity threshold;

If the first granularity information is not within the first preset dynamic granularity threshold, determine whether the first granularity information is within the second preset dynamic granularity threshold;

If the first granularity information is within the second preset dynamic granularity threshold, according to the detection unit, first real-time vibration data is obtained;

Obtaining second real-time vibration data according to the first real-time vibration data and the second preset dynamic granularity threshold, wherein the first real-time vibration data is smaller than the second real-time vibration data;

Obtain a first vibration instruction according to the vibration unit;

Vibrating the first screen according to the first vibration instruction according to the second real-time vibration data.
The method according to claim 2, wherein obtaining second real-time vibration data according to the first real-time vibration data and the second preset dynamic granularity threshold, the method further comprising:

Obtain first crushed material information of the first grinder;

Obtaining first hardness information according to the first pulverized material information;

According to the first image information, first roughness information is obtained, wherein the first roughness information is the surface roughness of the oversize;

perform vibration prediction according to the first hardness information and the first roughness information, and obtain first predicted vibration data;

The first predicted vibration data is used as the second real-time vibration data.
The method of claim 2, further comprising:

Obtaining first structure fabrication information of the first shredder;

producing information according to the first structure to obtain a first spatial distance;

Obtaining a first vibration amplitude according to the first spatial distance;

Constraining the first vibration amplitude as a first constraint condition of the second real-time vibration data.
The method of claim 3, further comprising:

obtaining a first working environment of the first pulverizer, wherein the first working environment includes an external environment and an internal environment;

Obtain first temperature information and first humidity information according to the first working environment;

Obtain a first environmental characteristic according to the first temperature information and the first humidity information;

According to the first pulverized material, a first attribute feature is obtained, wherein the first attribute feature includes a material high temperature feature and a material humidity feature;

generating a first impact index according to the first environmental characteristics and the first attribute characteristics;

According to the first impact index, a first early warning signal is obtained.
The method according to claim 1, wherein said obtaining the first interlock instruction according to the third judgment result, said method further comprising:

If the first interlock information and the second interlock information in the third judgment result do not meet the predetermined requirements at the same time, the first interlock instruction is obtained, wherein the predetermined requirements are in the logic judgment state "Yes" status for ;

If the first interlocking information satisfies the predetermined requirement in the third judgment result, and the second interlocking information does not meet the predetermined requirement, a first speed regulation command is obtained, wherein the first The speed regulation command is used to adjust the speed of the first pulverizer;

If the first interlocking information does not meet the predetermined requirement in the third judgment result, and the second interlocking information meets the predetermined requirement, a first maintenance instruction is obtained, wherein the first maintenance Instructions are for servicing the first screen.
The method according to claim 5, said generating a first impact index according to said first environmental characteristics and said first attribute characteristics, said method further comprising:

Constructing a material impact training model using the first environmental feature and the first attribute feature as input information;

The material impact training model is obtained by training multiple sets of training data until convergence, wherein each set of data in the multiple sets of training data includes the first environmental feature, the first attribute feature and the - identification information of the impact index;

An output result of the material impact training model is obtained, where the output result includes the first impact index.
An intelligent detection system for a pulverizer sieve, wherein the system includes:

A first obtaining unit, the first obtaining unit is used to obtain the first image information of the oversize of the first pulverizer according to the first camera;

A second obtaining unit, configured to obtain first granularity information by performing edge detection on the first image information;

A first judging unit, the first judging unit is used to judge whether the first granularity information is within a first preset dynamic granularity threshold, and obtain a first judging result;

a first operation unit, the first operation unit is configured to use the first judgment result as the first interlock information;

A third obtaining unit, the third obtaining unit is configured to obtain first current monitoring information by performing current monitoring on the first pulverizer;

A second judging unit, the second judging unit is used to judge whether the first screen is in a damaged state according to the first current monitoring information, and obtain a second judging result, wherein the oversize of the first pulverizer is in the above the first screen;

a second operation unit, the second operation unit is configured to use the second judgment result as the second interlock information;

a first input unit, configured to input the first interlock information and the second interlock information into a first interlock logic rule for judgment, and obtain a third judgment result;

A fourth obtaining unit, the fourth obtaining unit is configured to obtain the first interlock instruction according to the third judgment result;

A first interlock unit, the first interlock unit is used to interlock the first shredder according to the first interlock command.
An intelligent detection system for a pulverizer sieve, comprising at least one processor and a memory, the at least one processor is coupled to the memory, and is used to read and execute instructions in the memory, so as to perform the following claims 1- The method described in any one of 7.