Coal preparation plant system online diagnosis method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses a coal preparation plant system online diagnosis method and device, equipment and a storage medium. The method comprises the steps that fault judgment is carried out on system data in a data platform by calling any preset data judgment script, and the system data in the data platform is data obtained after digital twinborn calculation is carried out on a coal preparation plant system through a digital twinborn calculation model; and if the judgment result of the data judgment script is that the fault phenomenon exists, analyzing at least one fault reason causing the fault phenomenon and a processing opinion corresponding to each fault reason according to the fault phenomenon and a pre-established fault reason knowledge graph. On the basis, system data in the coal preparation plant system can be more comprehensively calculated and obtained through the digital twinborn calculation model, and when a fault phenomenon exists, the blockage fault of the coal preparation plant system can be more quickly analyzed based on the comprehensive system data by utilizing the characteristic that the relation of the fault reason knowledge graph is efficient.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of online diagnosis technology, and in particular to a method, device, equipment and storage medium for online diagnosis of a coal preparation plant system. Background Art

[0002] With the continuous development of automation technology, various factories have also upgraded their system automation control. Based on the upgraded automation control system, a host computer screen in the central control room is usually set up to display the key parameters of each key equipment in the factory system.

[0003] When a fault occurs, a reminder is usually given on the display interface of the host computer so that the staff can be informed of the fault in time, and then perform fault analysis, find the cause of the fault and eliminate the fault. The above process relies more on the work experience of the staff, and when performing fault analysis, it is sometimes necessary to arrive at the site, and the analysis takes a long time. If the fault cannot be eliminated in time, it may have a greater impact on the entire system. Summary of the invention

[0004] The embodiments of the present application provide a method, device, equipment and storage medium for online diagnosis of a coal preparation plant system to improve the efficiency of online diagnosis so as to eliminate faults in a timely manner.

[0005] In a first aspect, an embodiment of the present application provides a method for online diagnosis of a coal preparation plant system, the method comprising:

[0006] By calling any preset data judgment script, the system data in the data platform is judged for faults. The system data in the data platform is the data obtained by performing digital twin calculations on the coal preparation plant system using the digital twin calculation model;

[0007] If the judgment result of the data judgment script is that a fault phenomenon exists, based on the fault phenomenon and the pre-built fault cause knowledge graph, analyze at least one fault cause that causes the fault phenomenon and the corresponding handling opinions for each fault cause.

[0008] In a second aspect, an embodiment of the present application provides an online diagnosis device for a coal preparation plant system, the device comprising:

[0009] A fault judgment module is used to perform fault judgment on the system data in the data platform by calling any preset data judgment script. The system data in the data platform is the data obtained by performing digital twin calculation on the coal preparation plant system using the digital twin calculation model;

[0010] The analysis module is used to analyze at least one fault cause causing the fault phenomenon and the corresponding treatment opinions for each fault cause based on the fault phenomenon and the pre-built fault cause knowledge graph if the judgment result of the data judgment script is that a fault phenomenon exists.

[0011] In a third aspect, an embodiment of the present application further provides an electronic device, the electronic device comprising:

[0012] one or more processors;

[0013] a storage device for storing one or more programs,

[0014] When one or more programs are executed by one or more processors, the one or more processors implement the coal preparation plant system online diagnosis method provided in any embodiment of the present application.

[0015] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, characterized in that when the program is executed by a processor, an online diagnosis method for a coal preparation plant system as provided in any embodiment of the present application is implemented.

[0016] The technical solution of the embodiment of the present application is to perform fault judgment on the system data in the data platform by calling any preset data judgment script. The system data in the data platform is the data obtained after the digital twin calculation model is used to perform digital twin calculation on the coal preparation plant system; if the judgment result of the data judgment script is that there is a fault phenomenon, at least one fault cause causing the fault phenomenon and the corresponding treatment opinions for each fault cause are analyzed according to the fault phenomenon and the pre-built fault cause knowledge graph. Based on this, through the digital twin calculation model, a more comprehensive calculation and acquisition of the system data in the coal preparation plant system is achieved. When there is a fault phenomenon, the blocking fault of the coal preparation plant system can be analyzed more quickly based on the comprehensive system data and the efficient relationship characteristics of the fault cause knowledge graph. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a flow chart of an online diagnosis method for a coal preparation plant system provided in Example 1 of the present application;

[0018] Figure 2 A schematic diagram of a partial fault cause knowledge graph provided in Example 1 of the present application;

[0019] Figure 3 A schematic diagram of the structure of an online diagnostic device for a coal preparation plant system provided in Example 2 of the present application;

[0020] Figure 4 A schematic diagram of the structure of an electronic device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0021] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only the parts related to the present application, rather than all structures, are shown in the accompanying drawings.

[0022] Embodiment 1

[0023] Figure 1 A schematic diagram of a process flow of an online diagnosis method for a coal preparation plant system provided in Example 1 of the present application, as shown in FIG. Figure 1 As shown, the coal preparation plant system online diagnosis method provided in this embodiment can be applied to the coal preparation plant system online diagnosis platform mounted on a computer or other device with data processing capability, and can be used in conjunction with some application software to achieve a better experience. Specifically, the method may include the following steps:

[0024] Step 101: Perform fault judgment on the system data in the data platform by calling any preset data judgment script. The system data in the data platform is the data obtained after performing digital twin calculation on the coal preparation plant system using the digital twin calculation model.

[0025] In this step, the data judgment script may be a script stored in the data platform and used for fault judgment. Each data judgment script has its own unique identifier. This embodiment may call the corresponding data judgment script from the data platform through the unique identifier, and perform fault judgment by executing the data judgment script.

[0026] Specifically, the data judgment script can be manually written by operation and maintenance personnel and stored in the data platform. For each data judgment script, the corresponding system data will usually be obtained when it is executed. The system data is also stored in the data platform, so that when the data judgment script is executed, it can be directly obtained without transfer or interface, thereby improving the execution efficiency of the data judgment script.

[0027] In addition, when using the digital twin calculation model to perform digital twin calculations on the coal preparation plant system, the digital twin calculation model can be used to determine the production parameter indicators of each process operation link in the coal preparation process based on the raw coal sample screening data, floating and sinking data, and coal slime step-by-step release data, real-time raw coal washing volume, and the process flow calculation model within the digital twin entered into the coal quality information management system; the production parameter indicators are stored as system data in the data platform.

[0028] Among them, the process flow calculation model can include but is not limited to: number and mass calculation model, water volume and medium volume calculation model. The process operation links can include: screening, crushing, desliming, two-product heavy medium separation, three-product heavy medium separation, pre-de-mediuming, de-mediuming, screening dehydration, centrifugal dehydration, diversion, magnetic separation, hydraulic classification, coarse coal slime separation, flotation, concentration, combined medium preparation, circulating water, filtration, distribution, blending, etc.

[0029] The production index parameters may include: Q (output t / h), r (yield %), V (suspension volume m3 / h), G (solid amount in suspension t / h), Gc (total amount of non-magnetic matter in suspension t / h), Gf (total amount of magnetic matter in suspension t / h), W circulation (circulating water volume m3 / h), W (reference flow rate m3 / h); the quality indicators include: Ad (reference ash content %), ρ (suspension density t / m3), rc (non-magnetic matter content in suspension %), rf (magnetic matter content in suspension %), g (solid weight per unit volume of suspension t / m3), Mt (water content %).

[0030] It should be noted that after the above-mentioned process indicator parameters are calculated, they can be allocated to specific equipment according to the equipment parameter allocation model according to the allocation rules. At the same time, the production sequence can be set according to the actual downstream distance, material speed and other relationships on site. At this point, each device will have real-time coal flow, water flow, medium volume and some equipment parameters (current, etc.) and sensor parameters (flow, liquid level, temperature, etc.) connected to the system. These data are uniformly transmitted to the data platform.

[0031] It should be noted that the specific twin computing process of the above-mentioned data twin computing model can be referred to relevant technologies and will not be repeated here.

[0032] In addition, when judging whether there is a fault phenomenon, the data judgment script can judge whether the system data is in the normal range under the current raw coal supply level. If it is in the normal range, it will continue to call the data judgment script's identification in a patrol manner to make a judgment. If it is not in the normal range, it is determined that a fault phenomenon exists, that is, a certain system data is higher than a normal range or lower than a normal range, etc.

[0033] In a specific example, the abnormal judgment logic of the liquid level of the China Coal Magnetic Separation Tailings Bucket pre-stored in the data platform is called: the current liquid level value of the China Coal Magnetic Separation Tailings Bucket is greater than 50% (according to the threshold upper limit of the instantaneous coal content and water level matching of the raw coal) for 20 seconds. If it is found that the attribute value has been greater than 50% for more than 20 seconds, it is determined that there is a fault phenomenon, which is that the current liquid level value of the China Coal Magnetic Separation Tailings Bucket is greater than 50% for more than 20 seconds.

[0034] Step 102: If the judgment result of the data judgment script is that a fault phenomenon exists, analyze at least one fault cause causing the fault phenomenon and the corresponding treatment opinions for each fault cause based on the fault phenomenon and the pre-built fault cause knowledge graph.

[0035] In this step, you can first search the pre-built fault cause knowledge graph to see whether there is a target knowledge graph entity corresponding to the fault phenomenon.

[0036] If it exists, according to the relationship between the target knowledge graph entity and other entities in the fault cause knowledge graph, at least one knowledge graph cause entity and the knowledge graph processing opinion entity corresponding to each knowledge graph cause entity are matched; for any knowledge graph cause entity, the entity content of the knowledge graph cause entity is determined as the fault cause, and the entity content of the knowledge graph processing opinion entity corresponding to the knowledge graph cause entity is determined as the processing opinion corresponding to the fault cause.

[0037] It should be noted that the knowledge graph includes the relationship between knowledge graph entities and each knowledge graph. Therefore, in this step, you can first find out whether there is a target knowledge graph entity corresponding to the fault phenomenon. Among them, you can poll the knowledge graph entities in the pre-built fault cause knowledge graph; each time a knowledge graph entity is polled, the entity content in the knowledge graph entity is obtained, and the similarity between the fault phenomenon and the entity content is determined; if the result of the similarity determination is similar, the knowledge graph entity is determined as the target knowledge graph entity; if the result of the similarity determination is not similar, the next knowledge graph entity is polled until all knowledge graph entities in the fault cause knowledge graph are polled.

[0038] In a specific example, the knowledge graph entities in the fault cause knowledge graph are polled. When a certain entity is polled, such as Figure 2 As shown, Figure 2 This is a schematic diagram of a partial fault cause knowledge graph provided in Example 1 of the present application. When the entity "The level of the tail bucket of China Coal Magnetics has increased sharply" is polled, its entity content is "The level of the tail bucket of China Coal Magnetics has increased sharply". The similarity between the entity content and the aforementioned fault phenomenon is determined.

[0039] When making a specific determination, a semantic similarity determination may be made, for example, by using a pre-trained semantic similarity model to obtain a similarity determination result output by the model. It should be noted that the training and use of the semantic similarity model may refer to related technologies and will not be described in detail here.

[0040] If they are similar, the entity of "the level of the tail bucket of China Coal increases sharply" is determined as the target knowledge graph entity. Otherwise, continue polling.

[0041] It should be noted that after polling all knowledge graph entities in the fault cause knowledge graph and failing to obtain the target knowledge graph entity, a manual processing prompt is performed; the fault cause and the system operation after the manual processing prompt is issued are obtained, and the fault cause knowledge graph is expanded based on the fault cause and the system operation.

[0042] Specifically, the graph can be extracted using a knowledge graph extraction tool in a natural language manner, thereby extracting the aforementioned fault causes and system operations into the form of entities and relationships, and then expanding them into the fault cause knowledge graph.

[0043] In addition, when matching the knowledge graph cause entity and the corresponding knowledge graph processing opinion entity, you can first obtain the first knowledge graph entity that has a first category relationship with the target knowledge graph entity, and obtain the second knowledge graph entity that has a second category relationship with the first knowledge graph; then, check the second knowledge graph entity according to the system data in the data platform, and determine the second knowledge graph entity that meets the preset checking conditions as the knowledge graph cause entity; finally, determine the third knowledge graph entity that has a third category relationship with the knowledge graph cause entity as the corresponding knowledge graph processing opinion entity.

[0044] It should be noted that the relationships between entities in this embodiment can be of multiple categories. For example, the first category of relationships is used to indicate one or some fault phenomena caused by a physical fault; the second category of relationships can be used to indicate the cause of a physical fault; and the third category of relationships can indicate the treatment opinions that can be adopted for the cause of the fault.

[0045] This embodiment can quickly find the physical fault corresponding to the fault phenomenon, the cause of the physical fault and the corresponding handling suggestions through the relationship between different categories.

[0046] like Figure 2 As shown, the current liquid level value of the China Coal Magnetic Separation Tailings Bucket is greater than 50% and lasts for more than 20 seconds. Through the first category relationship (cause), the corresponding physical fault can be found that the feeding of the bucket is normal, but the discharge pipeline is blocked, and only the material enters but not exits, causing the bucket level to increase sharply. Further analysis of the cause of the blockage of the discharge pipeline shows that the upstream equipment of the magnetic tail bucket is the China Coal Crusher, and the current of the crusher is also in a relatively large state during this period. It can be inferred that because the China Coal Crusher has a large load, the material is not completely crushed and enters the magnetic tail bucket, blocking the pipeline during discharge. But why is the China Coal Crusher under high load? It is found that the common causes of this phenomenon are process-related, coal quality-related, and equipment-related. Then, the fault is investigated according to the conditions of each fault:

[0047] 1. The raw coal belt scale shows that the raw coal quantity is at the normal production level during this period, so this reason should be eliminated;

[0048] 2. The upstream sorting equipment of the medium coal crusher is a heavy medium cyclone. Poor sorting density control of the heavy medium cyclone will cause the clean coal to escape. However, the density meter data shows that the density control is stable during this period, so this reason is ruled out.

[0049] 3. The quality of raw coal changes. There are too many large particles. The proportion of feed in the heavy medium separation stage increases, resulting in an increase in the amount of medium coal and poor crushing effect of the crusher. According to the coal quality correction model of the digital twin, it is found that the coal quality has indeed changed during this period. At the same time, the calculation results of the digital quality calculation model show that the amount of medium coal during this period is too large, so it can be judged that this reason is valid;

[0050] 4. The crusher itself is faulty. According to the parameter data of the crusher connected to the system, except for the large current value, there is no other abnormality. This reason has a low priority.

[0051] 5. A large piece is stuck, the crushing effect is poor, and large particles enter the magnetic tail bucket, blocking the pipeline. This reason is also valid, but the fundamental reason that has been clarified is the change in coal quality and the increase in large pieces. This reason may be a direct cause, but not the fundamental cause, and can be output synchronously.

[0052] Based on the above analysis, the following root causes can be obtained, and in this embodiment, the knowledge graph cause entities and the corresponding knowledge graph processing opinion entities can be sorted and pushed according to the priority of the knowledge graph cause entities.

[0053] Therefore, the root causes of the abnormal liquid level in the tail bucket of China Coal may be (arranged in order of priority):

[0054] 1. Changes in coal quality, large pieces of material, resulting in high load on the coal crusher, poor crushing effect, large particles entering the coal magnetic tail barrel, and blocking the discharge pipeline - it is recommended to reduce the amount of raw coal - the system automatically adjusts the frequency of the coal feeder under the raw coal bunker to reduce the amount of raw coal, or manually replace the raw coal bunker;

[0055] 2. Occasional blockage of a large piece is caused by changes in coal quality. It is recommended to reduce the amount of raw coal - the system automatically adjusts the frequency of the coal feeder under the raw coal bunker, reduces the amount of raw coal or manually replaces the raw coal bunker;

[0056] 3. If the device itself fails, manual troubleshooting is recommended.

[0057] In this embodiment, by calling any preset data judgment script, the system data in the data platform is judged for faults. The system data in the data platform is the data obtained after the digital twin calculation model is used to calculate the coal preparation plant system; if the judgment result of the data judgment script is that there is a fault phenomenon, at least one fault cause causing the fault phenomenon and the corresponding treatment opinions for each fault cause are analyzed according to the fault phenomenon and the pre-built fault cause knowledge graph. Based on this, through the digital twin calculation model, a more comprehensive calculation and acquisition of the system data in the coal preparation plant system is achieved. When there is a fault phenomenon, the blocking fault of the coal preparation plant system can be analyzed more quickly based on the comprehensive system data and the efficient relationship characteristics of the fault cause knowledge graph.

[0058] Embodiment 2

[0059] Figure 3 This is a schematic diagram of the structure of an online diagnosis device for a coal preparation plant system provided in the second embodiment of the present application. The online diagnosis device for a coal preparation plant system provided in the embodiment of the present application can execute the online diagnosis method for a coal preparation plant system provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method. The device can be implemented in software and / or hardware, such as Figure 3 As shown, the online diagnosis device of the coal preparation plant system specifically includes: a fault determination module 301 and an analysis module 302.

[0060] Among them, the fault judgment module is used to perform fault judgment on the system data in the data platform by calling any preset data judgment script. The system data in the data platform is the data obtained after the digital twin calculation of the coal preparation plant system is performed using the digital twin calculation model;

[0061] The analysis module is used to analyze at least one fault cause causing the fault phenomenon and the corresponding treatment opinions for each fault cause based on the fault phenomenon and the pre-built fault cause knowledge graph if the judgment result of the data judgment script is that a fault phenomenon exists.

[0062] Furthermore, the analysis module is specifically used for:

[0063] Search the pre-built fault cause knowledge graph to see if there is a target knowledge graph entity corresponding to the fault phenomenon;

[0064] If it exists, at least one knowledge graph cause entity and the knowledge graph processing opinion entity corresponding to each knowledge graph cause entity are matched according to the relationship between the target knowledge graph entity and other entities in the fault cause knowledge graph;

[0065] For any knowledge graph cause entity, the entity content of the knowledge graph cause entity is determined as the cause of the fault, and the entity content of the knowledge graph processing opinion entity corresponding to the knowledge graph cause entity is determined as the processing opinion corresponding to the fault cause.

[0066] Furthermore, the analysis module is specifically used for:

[0067] Poll the knowledge graph entities in the pre-built fault cause knowledge graph;

[0068] Each time a knowledge graph entity is polled, the entity content in the knowledge graph entity is obtained, and the similarity between the fault phenomenon and the entity content is determined;

[0069] If the result of the similarity determination is similar, the knowledge graph entity is determined as the target knowledge graph entity;

[0070] If the result of the similarity determination is dissimilar, the next knowledge graph entity is polled until all knowledge graph entities in the fault cause knowledge graph are polled.

[0071] Furthermore, the device is specifically used for:

[0072] After polling all knowledge graph entities in the fault cause knowledge graph and failing to obtain the target knowledge graph entity, a manual processing prompt is provided;

[0073] Obtain the cause of the fault and the system operation after the manual processing prompt is issued, and expand the fault cause knowledge graph based on the fault cause and system operation.

[0074] Furthermore, the analysis module is specifically used for:

[0075] Obtain a first knowledge graph entity having a first category relationship with a target knowledge graph entity, and obtain a second knowledge graph entity having a second category relationship with the first knowledge graph;

[0076] The second knowledge graph entity is checked according to the system data in the data platform, and the second knowledge graph entity that meets the preset checking conditions is determined as the knowledge graph cause entity;

[0077] The third knowledge graph entity having a third category relationship with the knowledge graph cause entity is determined as the corresponding knowledge graph processing opinion entity.

[0078] Furthermore, the device is specifically used for:

[0079] The knowledge graph cause entities and the corresponding knowledge graph processing opinion entities are sorted and pushed according to the priority of the knowledge graph cause entities.

[0080] Furthermore, the device is specifically used for:

[0081] Using the digital twin calculation model, the production parameter indicators of each process operation link in the coal preparation process are determined based on the raw coal sample screening data, floating and sinking data, and step-by-step release data of coal slime, the real-time raw coal washing volume, and the process flow calculation model inside the digital twin, which are entered into the coal quality information management system;

[0082] The production parameter indicators are stored as system data in the data platform.

[0083] Embodiment 3

[0084] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present application is shown in FIG. Figure 4 As shown, the electronic device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of the processor 410 in the electronic device can be one or more. Figure 4 A processor 410 is taken as an example; the processor 410, the memory 420, the input device 430 and the output device 440 in the electronic device can be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0085] The memory 420 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the online diagnosis method for a coal preparation plant system in the embodiment of the present invention. The processor 410 executes various functional applications and data processing of the electronic device by running the software programs, instructions and modules stored in the memory 420, that is, to implement the above-mentioned online diagnosis method for a coal preparation plant system:

[0086] By calling any preset data judgment script, the system data in the data platform is judged for faults. The system data in the data platform is the data obtained by performing digital twin calculations on the coal preparation plant system using the digital twin calculation model;

[0087] If the judgment result of the data judgment script is that a fault phenomenon exists, based on the fault phenomenon and the pre-built fault cause knowledge graph, analyze at least one fault cause that causes the fault phenomenon and the corresponding handling opinions for each fault cause.

[0088] Furthermore, based on the fault phenomenon and the pre-built fault cause knowledge graph, at least one fault cause causing the fault phenomenon and the corresponding treatment opinions for each fault cause are analyzed, including:

[0089] Search the pre-built fault cause knowledge graph to see if there is a target knowledge graph entity corresponding to the fault phenomenon;

[0090] If it exists, at least one knowledge graph cause entity and the knowledge graph processing opinion entity corresponding to each knowledge graph cause entity are matched according to the relationship between the target knowledge graph entity and other entities in the fault cause knowledge graph;

[0091] For any knowledge graph cause entity, the entity content of the knowledge graph cause entity is determined as the cause of the fault, and the entity content of the knowledge graph processing opinion entity corresponding to the knowledge graph cause entity is determined as the processing opinion corresponding to the fault cause.

[0092] Furthermore, the pre-built fault cause knowledge graph is searched to see whether there is a target knowledge graph entity corresponding to the fault phenomenon, including:

[0093] Poll the knowledge graph entities in the pre-built fault cause knowledge graph;

[0094] Each time a knowledge graph entity is polled, the entity content in the knowledge graph entity is obtained, and the similarity between the fault phenomenon and the entity content is determined;

[0095] If the result of the similarity determination is similar, the knowledge graph entity is determined as the target knowledge graph entity;

[0096] If the result of the similarity determination is dissimilar, the next knowledge graph entity is polled until all knowledge graph entities in the fault cause knowledge graph are polled.

[0097] Furthermore, the method also includes:

[0098] After polling all knowledge graph entities in the fault cause knowledge graph and failing to obtain the target knowledge graph entity, a manual processing prompt is provided;

[0099] Obtain the cause of the fault and the system operation after the manual processing prompt is issued, and expand the fault cause knowledge graph based on the fault cause and system operation.

[0100] Furthermore, according to the relationship between the target knowledge graph entity and other entities in the fault cause knowledge graph, at least one knowledge graph cause entity and the knowledge graph processing opinion entity corresponding to each knowledge graph cause entity are matched, including:

[0101] Obtain a first knowledge graph entity having a first category relationship with a target knowledge graph entity, and obtain a second knowledge graph entity having a second category relationship with the first knowledge graph;

[0102] The second knowledge graph entity is checked according to the system data in the data platform, and the second knowledge graph entity that meets the preset checking conditions is determined as the knowledge graph cause entity;

[0103] The third knowledge graph entity having a third category relationship with the knowledge graph cause entity is determined as the corresponding knowledge graph processing opinion entity.

[0104] Furthermore, the method also includes:

[0105] The knowledge graph cause entities and the corresponding knowledge graph processing opinion entities are sorted and pushed according to the priority of the knowledge graph cause entities.

[0106] Furthermore, the method also includes:

[0107] Using the digital twin calculation model, the production parameter indicators of each process operation link in the coal preparation process are determined based on the raw coal sample screening data, floating and sinking data, and step-by-step release data of coal slime, the real-time raw coal washing volume, and the process flow calculation model inside the digital twin, which are entered into the coal quality information management system;

[0108] The production parameter indicators are stored as system data in the data platform.

[0109] The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 420 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 420 may further include a memory remotely arranged relative to the processor 410, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0110] Embodiment 4

[0111] Embodiment 4 of the present application further provides a storage medium containing computer executable instructions, which are used to execute a coal preparation plant system online diagnosis method when executed by a computer processor, the method comprising:

[0112] By calling any preset data judgment script, the system data in the data platform is judged for faults. The system data in the data platform is the data obtained by performing digital twin calculations on the coal preparation plant system using the digital twin calculation model;

[0113] If the judgment result of the data judgment script is that a fault phenomenon exists, based on the fault phenomenon and the pre-built fault cause knowledge graph, analyze at least one fault cause that causes the fault phenomenon and the corresponding handling opinions for each fault cause.

[0114] Furthermore, based on the fault phenomenon and the pre-built fault cause knowledge graph, at least one fault cause causing the fault phenomenon and the corresponding treatment opinions for each fault cause are analyzed, including:

[0115] Search the pre-built fault cause knowledge graph to see if there is a target knowledge graph entity corresponding to the fault phenomenon;

[0116] If it exists, at least one knowledge graph cause entity and the knowledge graph processing opinion entity corresponding to each knowledge graph cause entity are matched according to the relationship between the target knowledge graph entity and other entities in the fault cause knowledge graph;

[0117] For any knowledge graph cause entity, the entity content of the knowledge graph cause entity is determined as the cause of the fault, and the entity content of the knowledge graph processing opinion entity corresponding to the knowledge graph cause entity is determined as the processing opinion corresponding to the fault cause.

[0118] Furthermore, the pre-built fault cause knowledge graph is searched to see whether there is a target knowledge graph entity corresponding to the fault phenomenon, including:

[0119] Poll the knowledge graph entities in the pre-built fault cause knowledge graph;

[0120] Each time a knowledge graph entity is polled, the entity content in the knowledge graph entity is obtained, and the similarity between the fault phenomenon and the entity content is determined;

[0121] If the result of the similarity determination is similar, the knowledge graph entity is determined as the target knowledge graph entity;

[0122] If the result of the similarity determination is dissimilar, the next knowledge graph entity is polled until all knowledge graph entities in the fault cause knowledge graph are polled.

[0123] Furthermore, the method also includes:

[0124] After polling all knowledge graph entities in the fault cause knowledge graph and failing to obtain the target knowledge graph entity, a manual processing prompt is provided;

[0125] Obtain the cause of the fault and the system operation after the manual processing prompt is issued, and expand the fault cause knowledge graph based on the fault cause and system operation.

[0126] Furthermore, according to the relationship between the target knowledge graph entity and other entities in the fault cause knowledge graph, at least one knowledge graph cause entity and the knowledge graph processing opinion entity corresponding to each knowledge graph cause entity are matched, including:

[0127] Obtain a first knowledge graph entity having a first category relationship with a target knowledge graph entity, and obtain a second knowledge graph entity having a second category relationship with the first knowledge graph;

[0128] The second knowledge graph entity is checked according to the system data in the data platform, and the second knowledge graph entity that meets the preset checking conditions is determined as the knowledge graph cause entity;

[0129] The third knowledge graph entity having a third category relationship with the knowledge graph cause entity is determined as the corresponding knowledge graph processing opinion entity.

[0130] Furthermore, the method also includes:

[0131] The knowledge graph cause entities and the corresponding knowledge graph processing opinion entities are sorted and pushed according to the priority of the knowledge graph cause entities.

[0132] Furthermore, the method also includes:

[0133] Using the digital twin calculation model, the production parameter indicators of each process operation link in the coal preparation process are determined based on the raw coal sample screening data, floating and sinking data, and step-by-step release data of coal slime, the real-time raw coal washing volume, and the process flow calculation model inside the digital twin, which are entered into the coal quality information management system;

[0134] The production parameter indicators are stored as system data in the data platform.

[0135] Of course, the storage medium containing computer executable instructions provided in the embodiment of the present application, whose computer executable instructions are not limited to the above method operations, can also execute related operations in the coal preparation plant system online diagnosis method provided in any embodiment of the present application.

[0136] Through the above description of the implementation method, the technicians in the relevant field can clearly understand that the present application can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0137] It is worth noting that in the embodiment of the above-mentioned search device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

[0138] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A coal preparation plant system online diagnosis method, characterized in that: The method comprises: By calling any preset data judgment script, a fault judgment is performed on the system data in the data platform, where the system data in the data platform is the data obtained after the digital twin calculation is performed on the coal preparation plant system using the digital twin calculation model; If the determination result of the data judgment script is that a fault phenomenon exists, at least one fault cause causing the fault phenomenon and the pre-built fault cause knowledge graph are analyzed as well as the corresponding treatment opinions for each of the fault causes.

2. The method according to claim 1, characterized in that The analyzing, based on the fault phenomenon and the pre-built fault cause knowledge graph, at least one fault cause causing the fault phenomenon and a handling opinion corresponding to each fault cause includes: Searching in the pre-built fault cause knowledge graph whether there is a target knowledge graph entity corresponding to the fault phenomenon; If so, according to the relationship between the target knowledge graph entity and other entities in the fault cause knowledge graph, at least one knowledge graph cause entity and the knowledge graph processing opinion entity corresponding to each knowledge graph cause entity are matched; For any knowledge graph cause entity, the entity content of the knowledge graph cause entity is determined as the cause of the fault, and the entity content of the knowledge graph processing opinion entity corresponding to the knowledge graph cause entity is determined as the processing opinion corresponding to the fault cause.

3. The method according to claim 2, characterized in that The searching whether there is a target knowledge graph entity corresponding to the fault phenomenon from the pre-built fault cause knowledge graph includes: Poll the knowledge graph entities in the pre-built fault cause knowledge graph; Each time a knowledge graph entity is polled, entity content in the knowledge graph entity is obtained, and similarity determination is performed between the fault phenomenon and the entity content; If the result of the similarity determination is similar, the knowledge graph entity is determined as a target knowledge graph entity; If the result of the similarity determination is dissimilar, the next knowledge graph entity is polled until all knowledge graph entities in the fault cause knowledge graph are polled.

4. The method according to claim 3, characterized in that The method further comprises: After all knowledge graph entities in the fault cause knowledge graph are polled and no target knowledge graph entity is obtained, a manual processing prompt is performed; The fault cause and the system operation after the manual processing prompt is issued are obtained, and the fault cause knowledge graph is expanded according to the fault cause and the system operation.

5. The method according to claim 2, characterized in that: The matching of at least one knowledge graph cause entity and a knowledge graph processing opinion entity corresponding to each knowledge graph cause entity according to the relationship between the target knowledge graph entity and other entities in the fault cause knowledge graph includes: Obtain a first knowledge graph entity having a first category relationship with the target knowledge graph entity, and obtain a second knowledge graph entity having a second category relationship with the first knowledge graph; Check the second knowledge graph entity according to the system data in the data platform, and determine the second knowledge graph entity that meets the preset checking condition as the knowledge graph cause entity; The third knowledge graph entity having a third category relationship with the knowledge graph cause entity is determined as the corresponding knowledge graph processing opinion entity.

6. The method according to claim 1, characterized in that The method further comprises: The knowledge graph cause entities and the corresponding knowledge graph processing opinion entities are sorted and pushed according to the priority of the knowledge graph cause entities.

7. The method according to claim 1, characterized in that The method further comprises: Using the digital twin calculation model, the production parameter indicators of each process operation link in the coal preparation process are determined based on the raw coal sample screening data, floating and sinking data, and step-by-step release data of coal slime, the real-time raw coal washing volume, and the process flow calculation model inside the digital twin, which are entered into the coal quality information management system; The production parameter index is stored as system data in the data platform.

8. An online diagnostic device for a coal preparation plant system, characterized in that: The device comprises: A fault judgment module, used to perform fault judgment on the system data in the data platform by calling any preset data judgment script, wherein the system data in the data platform is data obtained by performing digital twin calculation on the coal preparation plant system using a digital twin calculation model; The analysis module is used to analyze at least one fault cause causing the fault phenomenon and the corresponding treatment opinions for each fault cause based on the fault phenomenon and a pre-built fault cause knowledge graph if the judgment result of the data judgment script is that a fault phenomenon exists.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the coal preparation plant system online diagnosis method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the online diagnosis method for a coal preparation plant system as described in any one of claims 1 to 7 is implemented.

Images