Belt conveyor belt fault diagnosis method and device, storage medium and terminal

Abstract

The invention discloses a belt fault diagnosis method and device for a belt conveyor, a storage medium and a terminal, and the method comprises the steps: obtaining a target belt feature map of the belt conveyor; transmitting the target belt feature map to a fault diagnosis model, and outputting state information and type data of the target belt feature map by the fault diagnosis model; and when the state information of the target belt feature graph is a fault, obtaining a target maintenance suggestion from a fault diagnosis database based on a target fault type in the type data, and generating analysis maintenance data of the target belt feature graph based on a target fault level in the type data and the target maintenance suggestion. According to the invention, faults can be found and eliminated in time, and serious influence caused by further development of the faults is avoided; the problems that the number of operators is large and the working time is long during manual inspection of the belt conveyor belt are solved, manpower resources and overhaul cost are effectively saved, the working efficiency of belt maintenance is improved, and the equipment maintenance operation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of belt conveyor diagnosis, and in particular to a belt conveyor belt fault diagnosis method and device, a storage medium and a terminal. Background Art

[0002] Belt conveyors, also known as rubber belt conveyors, are widely used in a variety of industries, including home appliances, electronics, electrical appliances, machinery, tobacco, coal, injection molding, postal services, printing, and food, transporting a wide variety of objects. Belt conveyors offer high conveying capacity, long conveying distances, simple structure, ease of maintenance, and convenient programmable control and automated operation. They utilize the continuous or intermittent motion of the conveyor belt to transport items under 100 kg or powdered or granular materials. They operate at high speed, smoothly, and with low noise, and can transport up and down slopes.

[0003] When belt conveyors operate continuously at high speeds and heavy loads for extended periods, or when transporting hard, sharp ores, the belts in their drive systems are vulnerable components. Therefore, monitoring belt tears not only improves maintenance efficiency but is also crucial for the safe operation of belt conveyors.

[0004] Currently, the monitoring of belt conveyor belts is mostly carried out by manual inspection, which is costly and time-consuming, and may also lead to subjective omissions. Summary of the Invention

[0005] The technical problem to be solved by the present invention is that the current monitoring method of belt conveyor belts adopts manual inspection, which has large cost and time expenditures, and cannot avoid the situation of missed inspections caused by subjective problems during the manual inspection process.

[0006] In order to solve the above technical problems, the present invention provides a belt conveyor belt fault diagnosis method, comprising:

[0007] Obtaining a target belt characteristic map of a belt conveyor;

[0008] Transmitting the target belt characteristic graph to a fault diagnosis model, wherein the fault diagnosis model outputs state information and type data of the target belt characteristic graph;

[0009] When the status information of the target belt characteristic diagram indicates a fault, obtaining a target maintenance suggestion from a fault diagnosis database based on the target fault type in the type data, and generating analysis maintenance data of the target belt characteristic diagram based on the target fault level in the type data and the target maintenance suggestion;

[0010] Wherein, when the status information of the target belt characteristic diagram is normal, the type data is empty.

[0011] Preferably, the fault diagnosis database is obtained in the following manner:

[0012] Acquire belt history data, and extract all belt fault data from the belt history data;

[0013] generating a fault diagnosis database based on all the belt fault data;

[0014] Among them, the belt historical history data includes multiple belt history data, each belt history data includes a timestamp and a status code, the status code includes status information and a belt characteristic diagram, and when the status information is a fault, the status code also includes the fault type, maintenance suggestions and fault level; the fault diagnosis database includes multiple fault types and the maintenance suggestions and fault weights corresponding to each fault type.

[0015] Preferably, the fault diagnosis model is obtained in the following manner:

[0016] Acquire belt historical data, and acquire a training data set and a verification data set based on the belt historical data;

[0017] An initial training model is trained based on the training data set and the verification data set to obtain a fault diagnosis model.

[0018] Preferably, the initial training model is obtained through an SMO algorithm based on all fault types in the belt historical data and the fault weight of each fault type.

[0019] Preferably, the fault types include longitudinal scratches and transverse fractures, and the fault levels include light level and severe level.

[0020] Preferably, obtaining a target maintenance suggestion from a fault diagnosis database based on the target fault type in the type data includes:

[0021] Matching the target fault type with the fault types in the fault diagnosis database to obtain a matching fault type;

[0022] It is determined whether the matching fault type has a corresponding maintenance suggestion. If so, the corresponding maintenance suggestion is used as the target maintenance suggestion; otherwise, a general maintenance suggestion is used as the target maintenance suggestion.

[0023] Preferably, the belt conveyor belt fault diagnosis method further includes:

[0024] The analysis and maintenance data of the target belt characteristic diagram and the target belt characteristic diagram are sent to a front-end server.

[0025] In order to solve the above technical problems, the present invention also provides a belt conveyor belt fault diagnosis device, which includes a characteristic map acquisition module, a state determination module and an analysis and maintenance data acquisition module;

[0026] The characteristic map acquisition module is used to acquire a target belt characteristic map of the belt conveyor;

[0027] The state determination module is used to transmit the target belt characteristic diagram to the fault diagnosis model, and the fault diagnosis model outputs the state information and type data of the target belt characteristic diagram;

[0028] The analysis and maintenance data acquisition module is configured to, when the status information of the target belt characteristic diagram indicates a fault, acquire a target maintenance suggestion from a fault diagnosis database based on the target fault type in the type data, and generate analysis and maintenance data of the target belt characteristic diagram based on the target fault level in the type data and the target maintenance suggestion;

[0029] Wherein, when the status information of the target belt characteristic diagram is normal, the type data is empty.

[0030] In order to solve the above technical problems, the present invention also provides a storage medium on which a computer program is stored, characterized in that when the program is executed by a processor, the belt conveyor belt fault diagnosis method is implemented.

[0031] In order to solve the above technical problem, the present invention further provides a terminal, comprising: a processor and a memory, wherein the memory is communicatively connected to the processor;

[0032] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the belt conveyor belt fault diagnosis method.

[0033] Compared with the prior art, one or more embodiments of the above solutions may have the following advantages or beneficial effects:

[0034] The belt conveyor belt fault diagnosis method provided by the embodiment of the present invention can realize the timely discovery and elimination of faults, and avoid the serious impact caused by further development of the faults; alleviate the problems of a large number of operators and long working hours during manual inspection of the belt conveyor belt, effectively save human resources and overhaul costs, improve the work efficiency of belt maintenance and reduce equipment maintenance operation costs.

[0035] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0037] Figure 1 A schematic diagram showing a flow chart of a belt conveyor belt fault diagnosis method according to an embodiment of the present invention is shown;

[0038] Figure 2 The figure shows a schematic structural diagram of a belt conveyor belt fault diagnosis device according to a second embodiment of the present invention;

[0039] Figure 3 A schematic diagram of a process flow of a terminal in embodiment 4 of the present invention is shown. DETAILED DESCRIPTION

[0040] The following describes the embodiments of the present invention in detail with reference to the accompanying drawings and examples, so that the present invention can fully understand how to apply technical means to solve technical problems and achieve technical effects, and thus implement the invention accordingly. It should be noted that, as long as no conflict exists, the various embodiments of the present invention and the various features of the embodiments can be combined with each other, and the resulting technical solutions are all within the scope of protection of the present invention.

[0041] When belt conveyors operate continuously at high speeds and heavy loads for extended periods, or when transporting hard, sharp ores, the belts in their drive systems are vulnerable components. Therefore, monitoring belt tears not only improves maintenance efficiency but is also crucial for safe operation. Currently, belt conveyor belt monitoring is often performed manually, which is costly and time-consuming, and can also lead to subjective omissions.

[0042] Example 1

[0043] In order to solve the technical problems existing in the prior art, an embodiment of the present invention provides a belt conveyor belt fault diagnosis method.

[0044] Figure 1 FIG. 1 is a flow chart showing a method for diagnosing belt faults of a belt conveyor according to an embodiment of the present invention; FIG. Figure 1 As shown, the belt conveyor belt fault diagnosis method according to the embodiment of the present invention includes the following steps.

[0045] Step S101: Acquire a target belt characteristic map of a belt conveyor.

[0046] Specifically, industrial cameras are installed around the belt conveyor to capture working images of the belt conveyor. The industrial cameras are used to capture a belt feature image of the belt conveyor. To distinguish it from other belt feature images, this embodiment uses the newly captured belt feature image of the belt conveyor as the target belt feature image.

[0047] Step S102: transmitting the target belt characteristic diagram to the fault diagnosis model, and the fault diagnosis model outputs the state information and type data of the target belt characteristic diagram.

[0048] Specifically, a fault diagnosis model is first obtained. The fault diagnosis model is obtained by downloading or other reasonable means to obtain the belt conveyor's historical belt data. This data is periodic data for the belt conveyor and includes multiple belt history data. Each belt history data record includes fields such as a timestamp, device number, component number, and status code. The status code includes status information and a belt characteristic diagram. If the status code indicates a fault, the status code also includes the fault type, repair recommendations, and fault level. In other words, the belt history data includes both normal operation data and fault data for the belt conveyor.

[0049] Furthermore, the fault types in the belt's historical data include longitudinal scratches (long, narrow scratches on the belt surface) and transverse fractures (cracks on the belt edge), and each fault type is classified as either minor or severe. Each fault type is assessed differently. For example, for longitudinal scratches, a fault length greater than 10 cm is considered a severe fault; otherwise, it is considered a minor fault. For transverse fractures, a fault length greater than 5 cm is considered a major fault; otherwise, it is considered a minor fault.

[0050] For the belt history data, labels are set for the corresponding belt feature maps based on the status code information, fault type, and fault level in the belt history data to obtain a training sample set. The training sample set is then divided into a training data set and a validation data set.

[0051] Based on all fault types in the belt's historical data and the fault weight of each fault type, appropriate SMO algorithm parameters are selected, including kernel function type, penalty coefficient, etc., and their optimal values ​​are determined through cross-validation and other methods to obtain the initial training model.

[0052] The primary training model is trained based on the training dataset and evaluated based on the validation dataset. Metrics such as accuracy, recall, and F-value are calculated to assess the model's performance. If these metrics do not meet the requirements, the model is retrained based on the training dataset until they meet the requirements. This results in a fault diagnosis model.

[0053] After acquiring the fault diagnosis model, the target belt characteristic map is transferred to the fault diagnosis model, which then outputs the target belt characteristic map's status information and type data. The target belt characteristic map's status information can be either faulty or normal. When the target belt characteristic map's status information is normal, the corresponding type data is empty. If the target belt characteristic map's status information is faulty, the corresponding type data includes the target maintenance recommendation and the target fault level, and the process then proceeds to step S103.

[0054] Step S103, when the status information of the target belt characteristic diagram is fault, obtain target maintenance suggestions from the fault diagnosis database based on the target fault type in the type data, and generate analysis maintenance data of the target belt characteristic diagram based on the target fault level and target maintenance suggestions in the type data.

[0055] Specifically, a fault diagnosis database must be obtained. This is accomplished by first acquiring historical belt data, then extracting all belt fault data from this data. This data is then categorized and integrated based on fault type to create a fault diagnosis database. The database includes multiple fault types, along with corresponding repair recommendations and fault weights. The fault weight is the number of belt fault types identified in the total number of belt fault data.

[0056] The maintenance suggestions in the belt history data can add detailed maintenance instructions to the maintenance suggestions for the corresponding fault types in the fault diagnosis database for fault types that occur more frequently (that is, when the fault weight of the fault type is higher). This can further improve maintenance efficiency and equipment reliability.

[0057] After obtaining the fault diagnosis database, the target repair suggestion corresponding to the target fault type in the acquired type data can be obtained from the fault diagnosis database. The target repair suggestion specifically includes: matching the target fault type with all fault types in the fault diagnosis database to obtain a matching fault type; then determining whether the matching fault type has a corresponding repair suggestion. If so, the corresponding repair suggestion is used as the target repair suggestion. When there are many fault types or a new fault type appears, the belt history data may not have a corresponding repair suggestion for that fault type. In this case, a general repair suggestion can be used as the target repair suggestion for that fault type. Preferably, the repair suggestion can be set to replace the belt.

[0058] After obtaining the target maintenance recommendations, the target fault level and target maintenance recommendations in the acquired type data are used to generate analytical maintenance data for the target belt characteristic map. This data is then sent to the front-end server, where staff can design a maintenance plan based on the recommendations and fault level. For example, if the fault level is severe, indicating that the fault may affect the normal operation of the belt conveyor, an emergency maintenance plan is required. On the other hand, if the fault level is minor, indicating that the fault is unlikely to affect the normal operation of the belt conveyor, maintenance can be postponed until the belt conveyor stops operating.

[0059] Step S104: sending the analysis and maintenance data of the target belt characteristic diagram and the target belt characteristic diagram to the front-end server.

[0060] Specifically, the analysis and maintenance data of the target belt characteristic diagram and the target belt characteristic diagram are sent to the front-end server for staff to review and save the target belt characteristic diagram fault diagnosis data and results to the memory. When the data in the memory reaches a certain level, all the stored data is added to the belt historical data to update the belt historical data. At the same time, a new fault diagnosis model and a new fault diagnosis database are obtained based on the updated belt historical data.

[0061] The belt conveyor belt fault diagnosis method provided by the embodiments of the present invention enables timely fault detection and elimination, preventing further development and serious consequences. It also alleviates the problems of large numbers of operators and long working hours during manual inspections of belt conveyor belts, effectively saving human resources and overhaul costs, improving belt maintenance efficiency, and reducing equipment maintenance costs. This method can diagnose the cause of belt tearing failures, achieving an 80% diagnostic accuracy based on historical test data sets. Application of this method is expected to improve maintenance efficiency, shorten overhaul time, and avoid the economic losses caused by serious failures.

[0062] Example 2

[0063] In order to solve the technical problems existing in the prior art, an embodiment of the present invention provides a belt conveyor belt fault diagnosis device.

[0064] Figure 2 FIG2 shows a schematic diagram of the structure of a belt conveyor belt fault diagnosis device according to the second embodiment of the present invention; FIG3 shows a schematic diagram of the structure of a belt conveyor belt fault diagnosis device according to the second embodiment of the present invention; Figure 2 As shown, the belt conveyor belt fault diagnosis device according to the embodiment of the present invention includes a characteristic diagram acquisition module, a state determination module and an analysis and maintenance data acquisition module.

[0065] The feature map acquisition module is used to obtain the target belt feature map of the belt conveyor.

[0066] The state determination module is used to transmit the target belt characteristic diagram to the fault diagnosis model, and the fault diagnosis model outputs the state information and type data of the target belt characteristic diagram.

[0067] The analysis and maintenance data acquisition module is used to obtain target maintenance suggestions from the fault diagnosis database based on the target fault type in the type data when the status information of the target belt characteristic diagram is fault, and to generate analysis and maintenance data of the target belt characteristic diagram based on the target fault level and target maintenance suggestions in the type data.

[0068] Among them, when the status information of the target belt characteristic diagram is normal, the type data is empty.

[0069] The belt conveyor belt fault diagnosis device provided by the embodiment of the present invention can realize the timely detection and elimination of faults, and avoid the serious impact caused by further development of the faults; it alleviates the problems of a large number of operators and long working hours during manual inspection of the belt conveyor belt, effectively saves human resources and overhaul costs, improves the work efficiency of belt maintenance and reduces equipment maintenance operation costs.

[0070] Example 3

[0071] In order to solve the above technical problems existing in the prior art, an embodiment of the present invention further provides a storage medium storing a computer program, which, when executed by a processor, can implement all the steps in the belt conveyor belt fault diagnosis method in embodiment 1.

[0072] The specific steps of the belt conveyor belt fault diagnosis method and the beneficial effects obtained by applying the readable storage medium provided by the embodiment of the present invention are the same as those in Example 1 and will not be described in detail here.

[0073] It should be noted that the storage medium includes various media that can store program codes, such as ROM, RAM, magnetic disk or optical disk.

[0074] Example 4

[0075] In order to solve the above technical problems existing in the prior art, an embodiment of the present invention further provides a terminal.

[0076] Figure 3 The schematic diagram of the terminal structure of the fourth embodiment of the present invention is shown. Figure 3 In this embodiment, the terminal includes a processor and a memory connected to each other; the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory, so that when the terminal executes, all steps in the belt conveyor belt fault diagnosis method described in Example 1 can be implemented.

[0077] The specific steps of the belt conveyor belt fault diagnosis method and the beneficial effects obtained by applying the terminal provided by the embodiment of the present invention are the same as those in Example 1 and will not be described in detail here.

[0078] It should be noted that the memory may include random access memory (RAM) and may also include non-volatile memory (non-volatile memory), such as at least one disk storage. Similarly, the processor may also be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0079] Although the embodiments disclosed herein are as described above, the contents described herein are merely embodiments for facilitating understanding of the present invention and are not intended to limit the present invention. Any person skilled in the art may make any modifications and variations in the form and details of the embodiments without departing from the spirit and scope of the present invention. However, the scope of protection of the present invention shall remain subject to the scope defined by the appended claims.

Claims

1. A belt conveyor belt fault diagnosis method, comprising: Obtaining a target belt characteristic map of a belt conveyor; Transmitting the target belt characteristic graph to a fault diagnosis model, wherein the fault diagnosis model outputs state information and type data of the target belt characteristic graph; When the state information of the target belt characteristic diagram is a fault, a target maintenance suggestion is obtained from a fault diagnosis database based on the target fault type in the type data, and analysis maintenance data of the target belt characteristic diagram is generated based on the target fault level in the type data and the target maintenance suggestion; Among them, when the status information of the target belt characteristic diagram is normal, the type data is empty.

2. The diagnostic method according to claim 1, characterized in that The fault diagnosis database is obtained in the following manner: Acquire belt history data, and extract all belt fault data from the belt history data; generating a fault diagnosis database based on all the belt fault data; Among them, the belt historical history data includes multiple belt history data, each belt history data includes a timestamp and a status code, the status code includes status information and a belt characteristic diagram, and when the status information is a fault, the status code also includes a fault type, maintenance suggestions and fault level; the fault diagnosis database includes multiple fault types and the maintenance suggestions and fault weights corresponding to each fault type.

3. The diagnostic method according to claim 1, characterized in that: The fault diagnosis model is obtained in the following manner: Acquire historical data of the belt, and acquire a training data set and a verification data set based on the historical data of the belt; An initial training model is trained based on the training data set and the verification data set to obtain a fault diagnosis model.

4. The diagnostic method according to claim 3, characterized in that: The initial training model is based on all fault types in the belt historical data and the fault weight of each fault type, and is obtained through the SMO algorithm.

5. The diagnostic method according to claim 1, characterized in that: The failure types include longitudinal scratches and transverse fractures, and the failure levels include light and severe levels.

6. The diagnostic method according to claim 1, characterized in that: Acquiring a target maintenance suggestion from a fault diagnosis database based on the target fault type in the type data includes: Matching the target fault type with the fault types in the fault diagnosis database to obtain a matching fault type; It is determined whether the matching fault type has a corresponding maintenance suggestion. If so, the corresponding maintenance suggestion is used as a target maintenance suggestion; otherwise, a general maintenance suggestion is used as a target maintenance suggestion.

7. The diagnostic method according to claim 1, characterized in that: Also includes: The analysis and maintenance data of the target belt characteristic diagram and the target belt characteristic diagram are sent to a front-end server.

8. A belt conveyor belt fault diagnosis device, characterized in that: It includes a characteristic diagram acquisition module, a state determination module and an analysis and maintenance data acquisition module; The characteristic map acquisition module is used to acquire a target belt characteristic map of the belt conveyor; The state determination module is used to transmit the target belt characteristic diagram to the fault diagnosis model, and the fault diagnosis model outputs the state information and type data of the target belt characteristic diagram; The analysis and maintenance data acquisition module is used to obtain a target maintenance suggestion from a fault diagnosis database based on the target fault type in the type data when the state information of the target belt characteristic diagram is a fault, and generate analysis and maintenance data of the target belt characteristic diagram based on the target fault level in the type data and the target maintenance suggestion; Among them, when the status information of the target belt characteristic diagram is normal, the type data is empty.

9. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the belt conveyor belt fault diagnosis method according to any one of claims 1 to 7 is implemented.

10. A terminal, characterized in that: include: A processor and a memory, wherein the memory is communicatively connected to the processor; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the belt conveyor belt fault diagnosis method according to any one of claims 1 to 7.

Images