Reliability Optimization Method and System for a Sliding Bearing Used in a Crusher

Abstract

The present invention relates to the technical field of abnormal identification of sliding bearings, and specifically to a reliability optimization method and system for sliding bearings used in crushers; monitor the jaw crusher to obtain a first data set; monitor the sliding bearing to obtain a second data set; split the first data set and the second data set according to the working trajectory of the jaw crusher to obtain a first data subset and a second data subset; construct a processing abnormality identification model to identify the first data subset to obtain processing abnormal data; construct a bearing abnormality identification model to identify the second data subset to obtain bearing abnormal data; obtain a detection data set through the processing abnormal data and the bearing abnormal data; construct a reliability identification model to identify the detection data set to obtain a reliability coefficient. The present invention collects and identifies the working data of the jaw crusher and its sliding bearing to obtain a reliability coefficient, and accurately identifies and warns the reliability of the sliding bearing.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal identification of sliding bearings, and specifically to a method and system for optimizing the reliability of sliding bearings for crushers. Background Art

[0002] A crusher is a mechanical device that can break large pieces of materials into small pieces and material powders, and is widely used in industries such as mining, metallurgy, construction, and chemical production; according to different working principles and application scenarios of crushers, they can be divided into various types, including jaw crushers, impact crushers, cone crushers, and hammer crushers, etc.

[0003] The jaw crusher has the advantages of simple structure, reliable performance, and easy maintenance, and is suitable for the primary crushing of large pieces of materials. It is a common crushing equipment in the mining and construction industries; the jaw crusher mainly consists of a housing, a fixed jaw plate, a movable jaw plate, and an eccentric shaft; the movable jaw plate makes a reciprocating motion through the rotation of the eccentric shaft under the drive of the motor. When the movable jaw plate moves downward, the material falls into the crushing cavity under the action of gravity and is crushed in the gap between the movable jaw plate and the fixed jaw plate.

[0004] During the working process of the jaw crusher, the sliding bearing plays a crucial role; it is used to support the movable jaw and other rotating components, reduce friction, ensure the smooth operation of the movable jaw, and absorb impact force at the same time; its performance directly affects the working efficiency and service life of the equipment. However, due to factors such as harsh working environment and large load fluctuations, the sliding bearing is prone to abnormal conditions such as wear, overheating, and insufficient lubrication, resulting in equipment failures.

[0005] Therefore, it is necessary to monitor and identify the reliability of the sliding bearing in the jaw crusher to timely discover potential problems. This is of great significance for ensuring the normal operation of the crusher, reducing the fault shutdown time, and lowering the maintenance cost.

[0006] In the process of identifying the reliability of the sliding bearing in the prior art, it is mainly obtained and identified through the parameters of the sliding bearing itself, and the mechanical equipment where the sliding bearing is located has not been deeply studied, and the working scenario and equipment characteristics where the sliding bearing is located have not been considered, resulting in inaccurate identification of the reliability of the sliding bearing.

[0007] For this reason, a method and system for optimizing the reliability of sliding bearings for crushers are proposed. Summary of the Invention

[0008] The object of the present invention is to provide a method and system for optimizing the reliability of a sliding bearing for a crusher, which monitors a jaw crusher to obtain a first data set; monitors the sliding bearing to obtain a second data set; splits the first data set and the second data set according to the working trajectory of the jaw crusher to obtain a first data subset and a second data subset; constructs a machining anomaly recognition model to recognize the first data subset to obtain machining anomaly data; constructs a bearing anomaly recognition model to recognize the second data subset to obtain bearing anomaly data; obtains a detection data set through the machining anomaly data and the bearing anomaly data; constructs a reliability recognition model to recognize the detection data set to obtain a reliability coefficient. The present invention collects and recognizes the working data of the jaw crusher and its sliding bearing to obtain a reliability coefficient, and accurately recognizes and warns the reliability of the sliding bearing.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] A method for optimizing the reliability of a sliding bearing for a crusher, comprising:

[0011] S10. Monitor the working jaw crusher to obtain a first data set; the first data set includes material parameters, equipment parameters, material input data, and material output data;

[0012] S20. Obtain the working trajectory of the jaw crusher, and split the first data set according to the working trajectory to obtain a plurality of first data subsets; the first data subsets include a material parameter subset, an equipment parameter subset, a material input subset, and a material output subset;

[0013] S30. Construct a machining anomaly recognition model to recognize the first data subset, and recognize machining anomaly data through the data of material input and material output;

[0014] S40. Monitor the working sliding bearing to obtain a second data set, the second data set includes sliding bearing operation data, sliding bearing lubrication data, and sliding bearing temperature data;

[0015] S50. Split the second data set according to the working trajectory to obtain a plurality of second data subsets; the second data subsets include an operation data subset, a lubrication data subset, and a temperature data subset;

[0016] S60. Construct a bearing anomaly recognition model to recognize the second data subset, and recognize bearing anomaly data through the operation data subset, the lubrication data subset, and the temperature data subset;

[0017] S70. Integrate the detection data set by processing abnormal data of the material and abnormal data of the bearing; construct a reliability recognition model, and identify the detection data set through the reliability recognition model to obtain a reliability coefficient; perform abnormal recognition and early warning of the sliding bearing through the reliability coefficient.

[0018] The material parameters include material hardness, material humidity, and material viscosity; the equipment parameters include cumulative operating time, rotation speed setting, vibration frequency data, and vibration amplitude data; the material input data includes material input mass, material input shape, and material input particles; the material output data includes material output mass, material output shape, and material output particles.

[0019] The operating data of the sliding bearing includes bearing vibration frequency data, bearing amplitude data, bearing sound data, and bearing rotation speed data; the lubrication data of the sliding bearing includes lubricant viscosity data, lubricant color data, and lubricant texture data; the temperature data of the sliding bearing includes bearing temperature data.

[0020] The process of splitting the first data set through the working trajectory of the jaw crusher is as follows:

[0021] Identify the movement trajectory of the reciprocating movement of the movable jaw plate during the working process of the jaw crusher; take one reciprocating movement cycle of the movable jaw plate as the identification unit.

[0022] Obtain all the identification units of the jaw crusher; split the collected first data set through the time range where the identification unit is located to obtain the first data subset.

[0023] The processing abnormal recognition model includes an output prediction layer and a processing abnormal recognition layer.

[0024] The output prediction layer performs identification and prediction through the material parameter subset, equipment parameter subset, and material input subset in the first data subset to obtain a predicted output subset; the predicted output subset includes predicted output mass, predicted output shape, and predicted output particles.

[0025] The processing abnormal recognition layer performs comparative recognition on the predicted output subset and the material output subset, and identifies processing abnormal data through data differences.

[0026] The bearing abnormal recognition model includes an operation abnormal recognition layer, a lubrication abnormal recognition layer, and a temperature abnormal recognition layer.

[0027] The operation abnormal recognition layer is used to identify the operation data subset, and identify operation abnormal data through the bearing vibration frequency subset, bearing amplitude subset, bearing sound subset, and bearing rotation speed subset therein.

[0028] The lubrication anomaly identification layer is used to identify the lubrication data subset, and through the lubricant viscosity subset, lubricant color subset, and lubricant texture subset therein, the lubrication anomaly data is identified;

[0029] The temperature anomaly identification layer is used to identify the temperature data subset to obtain temperature anomaly data;

[0030] Bearing anomaly data is obtained based on the operation anomaly data, lubrication anomaly data, and temperature anomaly data.

[0031] The process of obtaining and identifying the detection data set is as follows:

[0032] The first data set and the second data set are respectively divided by the working trajectory of the jaw crusher to obtain a first data subset and a second data subset;

[0033] The machining anomaly data is obtained by identifying the first data subset through the machining anomaly identification model; the bearing anomaly data is obtained by identifying the second data subset through the bearing anomaly identification model;

[0034] The corresponding machining anomaly data and bearing anomaly data are obtained according to the working trajectory of the jaw crusher as the detection data subset;

[0035] All the detection data subsets are obtained and arranged in chronological order to obtain the detection data set;

[0036] The reliability coefficient is obtained by identifying the detection data set through the reliability identification model.

[0037] A reliability optimization system for a sliding bearing of a crusher, comprising:

[0038] The first data acquisition module monitors the working jaw crusher to obtain a first data set; the first data set includes material parameters, equipment parameters, material input data, and material output data;

[0039] The first data division module obtains the working trajectory of the jaw crusher and splits the first data set according to the working trajectory to obtain a plurality of first data subsets; the first data subsets include a material parameter subset, an equipment parameter subset, a material input subset, and a material output subset;

[0040] The first data identification module constructs a machining anomaly identification model to identify the first data subset, and through the data of material input and material output, the machining anomaly data is identified;

[0041] The second data acquisition module monitors the working sliding bearing to obtain a second data set, and the second data set includes sliding bearing operation data, sliding bearing lubrication data, and sliding bearing temperature data;

[0042] The second data partitioning module splits the second data set according to the working trajectory to obtain a plurality of second data subsets; the second data subsets include an operation data subset, a lubrication data subset, and a temperature data subset;

[0043] The second data recognition module constructs a bearing anomaly recognition model to recognize the second data subsets, and through the operation data subset, the lubrication data subset, and the temperature data subset, recognizes bearing anomaly data;

[0044] The anomaly recognition module integrates the machining anomaly data and the bearing anomaly data to obtain a detection data set; constructs a reliability recognition model, recognizes the detection data set through the reliability recognition model to obtain a reliability coefficient; and performs anomaly recognition and warning of the sliding bearing through the reliability coefficient.

[0045] The process of splitting the first data set according to the working trajectory of the jaw crusher is as follows:

[0046] Recognize the movement trajectory of the reciprocating movement of the movable jaw plate during the working process of the jaw crusher; take one reciprocating movement cycle of the movable jaw plate as the recognition unit;

[0047] Obtain all the recognition units of the jaw crusher; split the collected first data set through the time range where the recognition units are located to obtain first data subsets.

[0048] The machining anomaly recognition model includes an output prediction layer and a machining anomaly recognition layer;

[0049] The output prediction layer performs recognition and prediction through the material parameter subset, the equipment parameter subset, and the material input subset in the first data subset to obtain a prediction output subset; the prediction output subset includes predicted output quality, predicted output shape, and predicted output particles;

[0050] The machining anomaly recognition layer performs comparative recognition on the prediction output subset and the material output subset, and recognizes machining anomaly data through data differences.

[0051] The bearing anomaly recognition model includes an operation anomaly recognition layer, a lubrication anomaly recognition layer, and a temperature anomaly recognition layer;

[0052] The operation anomaly recognition layer is used to recognize the operation data subset, and through the bearing vibration frequency subset, the bearing amplitude subset, the bearing sound subset, and the bearing speed subset therein, recognizes operation anomaly data;

[0053] The lubrication anomaly recognition layer is used to recognize the lubrication data subset, and through the lubricant viscosity subset, the lubricant color subset, and the lubricant texture subset therein, recognizes lubrication anomaly data;

[0054] The temperature anomaly recognition layer is used to recognize the subset of temperature data to obtain temperature anomaly data;

[0055] Bearing anomaly data is obtained based on the operation anomaly data, lubrication anomaly data, and temperature anomaly data.

[0056] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0057] 1. The present invention constructs a processing anomaly recognition model to recognize the first data subset, and performs recognition and prediction through the material parameter subset, equipment parameter subset, and material input subset in the first data subset to obtain a predicted output subset; then, processing anomaly data is obtained based on the data difference between the predicted output subset and the material output subset; accurately recognize the material processing anomalies of the jaw crusher.

[0058] 2. The present invention constructs a bearing anomaly recognition model to recognize the second data subset. The operation anomaly recognition layer is used to recognize the operation data subset to obtain operation anomaly data; the lubrication anomaly recognition layer is used to recognize the lubrication data subset to obtain lubrication anomaly data; the temperature anomaly recognition layer is used to recognize the temperature data subset to obtain temperature anomaly data; bearing anomaly data is obtained through the operation anomaly data, lubrication anomaly data, and temperature anomaly data, and accurately recognize the operation conditions of the sliding bearing.

[0059] 3. During the working process of the jaw crusher, the present invention recognizes the reciprocating motion of the movable jaw plate, and uses the reciprocating motion as the recognition unit to recognize and divide the collected data set to obtain data subsets; then, based on the differences between the data subsets, recognize the material processing anomalies and abnormal changes in the operation conditions of the sliding bearing between different cycles, so as to recognize the anomalies of the sliding bearing and accurately predict its reliability. Description of the Drawings

[0060] Figure 1 is a schematic flow chart of a method for optimizing the reliability of a sliding bearing for a crusher according to the present invention;

[0061] Figure 2 is a schematic structural diagram of the processing anomaly recognition model of the present invention;

[0062] Figure 3 is a schematic structural diagram of the bearing anomaly recognition model of the present invention;

[0063] Figure 4 is a schematic structural diagram of a system for optimizing the reliability of a sliding bearing for a crusher according to the present invention. Detailed Embodiments

[0064] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0065] The jaw crusher has the advantages of simple structure, reliable performance, and easy maintenance, and is suitable for the primary crushing of large pieces of materials; it is a common crushing equipment in the mining and construction industries; during the working process of the jaw crusher, the sliding bearing plays a crucial role; it is used to support the movable jaw plate and other rotating components, can reduce friction, ensure smooth operation, and at the same time absorb impact force, and its performance directly affects the working efficiency and service life of the equipment. However, due to factors such as harsh working environment and large load fluctuations, the sliding bearing is prone to abnormal conditions such as wear, overheating, and insufficient lubrication, resulting in equipment failures.

[0066] Therefore, it is necessary to monitor and identify the reliability of the sliding bearing in the jaw crusher to timely discover potential problems. This is of great significance for ensuring the normal operation of the crusher, reducing the downtime due to failures, and lowering the maintenance cost.

[0067] For this reason, a method and system for optimizing the reliability of the sliding bearing for crushers are proposed.

[0068] Embodiment 1

[0069] The present invention proposes a method for optimizing the reliability of the sliding bearing for crushers, and its process is as Figure 1 shown, including:

[0070] S10. Monitor and identify the working jaw crusher to obtain the first data set; the first data set includes material parameters, equipment parameters, material input data, and material output data;

[0071] The material parameters include material hardness, material humidity, and material viscosity; the equipment parameters include cumulative operating time, rotation speed setting, vibration frequency data, and vibration amplitude data; the material input data includes material input mass, material input shape, and material input particles; the material output data includes material output mass, material output shape, and material output particles;

[0072] Among them, the material hardness refers to the ability of the material to resist plastic deformation or destruction, and is usually expressed by Mohs hardness or Brinell hardness, and is obtained by sampling and testing the material with a hardness testing device;

[0073] The material humidity refers to the water content in the material, which affects the efficiency and quality of the crushing process, and is obtained by sampling the material and performing a drying test;

[0074] The viscosity of the material is an index of the fluidity of the material, which affects the crushing and conveying processes and is detected through viscosity testing;

[0075] The vibration frequency data and vibration amplitude data are obtained by monitoring the working jaw crusher through Internet of Things detection devices.

[0076] The input mass of the material and the output mass of the material are obtained by the weighing method,

[0077] The input shape of the material, the input particles of the material, the output shape of the material, and the input particles of the material are obtained through image recognition.

[0078] In the present invention, the jaw crusher is monitored and data is recognized respectively to obtain a first data set; the first data set includes material parameters, equipment parameters, material input data, and material output data; through the collection of the above data, the working state of the jaw crusher can be accurately recognized.

[0079] S20. Obtain the working trajectory of the jaw crusher, and split the first data set according to the working trajectory to obtain a plurality of first data subsets; the first data subsets include a material parameter subset, an equipment parameter subset, a material input subset, and a material output subset.

[0080] The jaw crusher mainly includes a housing, a jaw plate, and an eccentric shaft; among them, the housing is a structural part that bears the entire equipment; the jaw plate includes a fixed jaw plate and a movable jaw plate; the eccentric shaft includes a sliding bearing.

[0081] During the working process, the eccentric shaft drives the movable jaw plate to perform a periodic reciprocating motion, so that the movable jaw plate moves up and down opposite to the fixed jaw plate. When the movable jaw plate moves downward, the discharge port becomes larger and the material can be discharged from the crusher. When the movable jaw plate moves upward, the material is clamped between the moving jaw and the fixed jaw and starts to be crushed. The material is subjected to strong extrusion and shear forces between the movable jaw plate and the fixed jaw plate, and after several crushings, the material is gradually crushed into the required particle size; when the material is crushed to a certain particle size, it is discharged through the discharge port.

[0082] The process of splitting the first data set through the working trajectory of the jaw crusher is as follows:

[0083] Identify the movement trajectory of the reciprocating movement of the movable jaw plate during the working process of the jaw crusher; use one reciprocating movement cycle of the movable jaw plate as the identification unit;

[0084] Obtain all the identification units of the jaw crusher; split the collected first data set according to the time range where the identification unit is located to obtain the first data subset.

[0085] Due to the influence of materials, the duration of the reciprocating motion of the jaw crusher is not necessarily the same.

[0086] In the working process of the jaw crusher of the present invention, the reciprocating motion of the movable jaw plate is identified, and its reciprocating motion is used as an identification unit to identify and divide the collected data set to obtain data subsets; through the data subsets, the anomalies between different cycles in the periodic operation of the jaw crusher can be accurately identified.

[0087] S30. Construct a processing anomaly identification model to identify the first data subset, and identify the processing anomaly data through the data differences between the material input and the material output.

[0088] The processing anomaly identification model is constructed based on a deep neural network model, and its structure is as Figure 2 shown, including an output prediction layer and a processing anomaly identification layer;

[0089] The output prediction layer performs identification and prediction through the material parameter subset, the equipment parameter subset, and the material input subset in the first data subset to obtain a predicted output subset; the predicted output subset includes predicted output quality, predicted output shape, and predicted output particles;

[0090] The processing anomaly identification layer performs comparative identification on the predicted output subset and the material output subset, and identifies the processing anomaly data through data differences.

[0091] The present invention constructs a processing anomaly identification model to identify the first data subset, performs identification and prediction through the material parameter subset, the equipment parameter subset, and the material input subset in the first data subset to obtain a predicted output subset; and then obtains the processing anomaly data according to the data differences between the predicted output subset and the material output subset; accurately identifies the processing anomalies of the jaw crusher.

[0092] S40. Monitor the sliding bearing during operation to obtain a second data set, which includes sliding bearing operation data, sliding bearing lubrication data, and sliding bearing temperature data.

[0093] The sliding bearing operation data includes bearing vibration frequency data, bearing amplitude data, bearing sound data, and bearing rotation speed data; the sliding bearing lubrication data includes lubricant viscosity data, lubricant color data, and lubricant texture data, which are obtained by detecting the lubricant used in the sliding bearing; the sliding bearing temperature data includes bearing temperature data.

[0094] During the operation of the jaw crusher, there is a certain correlation between the vibration data of the jaw crusher and the vibration data of its sliding bearing, but they are not exactly the same; this is because the influencing factors they are subject to are not exactly the same.

[0095] Among them, the vibration data of the jaw crusher, namely the vibration frequency data and vibration amplitude data in the equipment parameters, are obtained by averaging multiple sensors arranged at positions such as the housing and jaw plate of the jaw crusher; the vibration data of the sliding bearing is obtained by monitoring the sliding bearing.

[0096] S50. Split the second data set according to the working trajectory to obtain multiple second data subsets; the second data subsets include an operation data subset, a lubrication data subset, and a temperature data subset;

[0097] S60. Construct a bearing abnormality recognition model to recognize the second data subset, and through the operation data subset, lubrication data subset, and temperature data subset, recognize the bearing abnormality data;

[0098] The bearing abnormality recognition model is constructed based on a deep neural network model, and its structure is as Figure 3 shown, including an operation abnormality recognition layer, a lubrication abnormality recognition layer, and a temperature abnormality recognition layer;

[0099] The operation abnormality recognition layer is used to recognize the operation data subset, and through the bearing vibration frequency subset, bearing amplitude subset, bearing sound subset, and bearing rotation speed subset therein, recognize the operation abnormality data;

[0100] The lubrication abnormality recognition layer is used to recognize the lubrication data subset, and through the lubricant viscosity subset, lubricant color subset, and lubricant texture subset therein, recognize the lubrication abnormality data;

[0101] The temperature abnormality recognition layer is used to recognize the temperature data subset to obtain the temperature abnormality data;

[0102] Obtain the bearing abnormality data based on the operation abnormality data, lubrication abnormality data, and temperature abnormality data.

[0103] The present invention constructs a bearing abnormality recognition model to recognize the second data subset, obtains the operation abnormality data by recognizing the operation data subset through the operation abnormality recognition layer; obtains the lubrication abnormality data by recognizing the lubrication data subset through the lubrication abnormality recognition layer; obtains the temperature abnormality data by recognizing the temperature data subset through the temperature abnormality recognition layer; and obtains the bearing abnormality data through the operation abnormality data, lubrication abnormality data, and temperature abnormality data, accurately recognizing the operating condition of the sliding bearing.

[0104] S70. Integrate the machining abnormality data and bearing abnormality data to obtain a detection data set; construct a reliability recognition model, recognize the detection data set through the reliability recognition model to obtain a reliability coefficient; and perform abnormality recognition and early warning of the sliding bearing through the reliability coefficient.

[0105] The acquisition and recognition process of the detection data set is as follows:

[0106] The first data set and the second data set are respectively divided according to the working trajectory of the jaw crusher to obtain a first data subset and a second data subset;

[0107] The machining anomaly data is obtained by identifying the first data subset through a machining anomaly recognition model; the bearing anomaly data is obtained by identifying the second data subset through a bearing anomaly recognition model;

[0108] The corresponding machining anomaly data and bearing anomaly data are obtained according to the working trajectory of the jaw crusher as the detection data subset;

[0109] All the detection data subsets are obtained and arranged in chronological order to obtain the detection data set;

[0110] The reliability coefficient is obtained by identifying the detection data set through a reliability recognition model.

[0111] Based on the working trajectory of the jaw crusher, the present invention divides and identifies the collected data to obtain data subsets, and then identifies the abnormal changes between different cycles according to the differences between the data subsets, so as to identify the anomalies of the sliding bearing and accurately predict its reliability.

[0112] The present invention monitors the jaw crusher to obtain a first data set; monitors the sliding bearing to obtain a second data set; splits the first data set and the second data set according to the working trajectory of the jaw crusher to obtain a first data subset and a second data subset; constructs a machining anomaly recognition model to identify the first data subset to obtain machining anomaly data; constructs a bearing anomaly recognition model to identify the second data subset to obtain bearing anomaly data; obtains a detection data set through the machining anomaly data and the bearing anomaly data; constructs a reliability recognition model to identify the detection data set to obtain a reliability coefficient, and accurately identifies and warns the reliability of the sliding bearing.

[0113] Embodiment 2

[0114] During the material crushing process in Mine A using a jaw crusher, during the operation of the jaw crusher, due to the changes in the properties of the material and the processing environment, the sliding bearing of the jaw crusher is prone to abnormal conditions, affecting the reliability of the jaw crusher and even causing serious safety hazards.

[0115] To ensure the safe use of the jaw crusher, Mine A uses the reliability optimization system for the sliding bearing of a crusher described in the present invention for monitoring and identification.

[0116] The structure of the reliability optimization system for the sliding bearing used in a crusher is as follows Figure 4 shown, including:

[0117] A first data acquisition module, a first data partitioning module, a first data identification module, a second data acquisition module, a second data partitioning module, a second data identification module, and an anomaly identification module.

[0118] The first data acquisition module monitors the jaw crusher during operation to obtain a first data set; the first data set includes material parameters, equipment parameters, material input data, and material output data.

[0119] The material parameters include material hardness, material humidity, and material viscosity; the equipment parameters include cumulative operating time, speed setting, vibration frequency data, and vibration amplitude data; the material input data includes material input mass, material input shape, and material input particles; the material output data includes material output mass, material output shape, and material output particles;

[0120] The first data partitioning module obtains the working trajectory of the jaw crusher and splits the first data set according to the working trajectory to obtain multiple first data subsets; the first data subsets include material parameter subsets, equipment parameter subsets, material input subsets, and material output subsets.

[0121] The process of splitting the first data set through the working trajectory of the jaw crusher is as follows:

[0122] Identify the movement trajectory of the moving jaw plate during the operation of the jaw crusher; take one reciprocating movement cycle of the moving jaw plate as the identification unit;

[0123] Obtain all the identification units of the jaw crusher; split the collected first data set through the time range where the identification unit is located to obtain the first data subset.

[0124] The speed setting of the jaw crusher used in Mine A during operation is 200 revolutions per minute; due to different material characteristics, the speed also varies in the actual process. For the convenience of data partitioning and identification, Mine A partitions the first data set in units of ten identification units; to obtain the first data subset; the partitioning results of the data are shown in Table 1.

[0125] Table 1 Partitioning Results Table of the First Data Set of Mine A

[0126]

[0127] In the working process of the jaw crusher, the present invention identifies the reciprocating motion of the movable jaw plate, uses the reciprocating motion as an identification unit to identify and divide the collected data set to obtain data subsets, and can accurately identify the anomalies between different cycles during the periodic operation of the jaw crusher through the data subsets.

[0128] The first data identification module constructs a processing anomaly identification model to identify the first data subset, and identifies processing anomaly data through the data of material input and material output.

[0129] The processing anomaly identification model includes an output prediction layer and a processing anomaly identification layer;

[0130] The output prediction layer performs identification and prediction through the material parameter subset, equipment parameter subset, and material input subset in the first data subset to obtain a predicted output subset; the predicted output subset includes predicted output quality, predicted output shape, and predicted output particles.

[0131] The processing anomaly identification layer performs comparative identification on the predicted output subset and the material output subset, and identifies processing anomaly data through data differences.

[0132] The present invention constructs a processing anomaly identification model to identify the first data subset, performs identification and prediction through the material parameter subset, equipment parameter subset, and material input subset in the first data subset to obtain a predicted output subset, and then obtains processing anomaly data based on the data differences between the predicted output subset and the material output subset, accurately identifying the processing anomalies of the jaw crusher.

[0133] The second data acquisition module monitors the sliding bearing during operation to obtain a second data set, and the second data set includes sliding bearing operation data, sliding bearing lubrication data, and sliding bearing temperature data.

[0134] The sliding bearing operation data includes bearing vibration frequency data, bearing amplitude data, bearing sound data, and bearing rotation speed data; the sliding bearing lubrication data includes lubricant viscosity data, lubricant color data, and lubricant texture data, which are obtained by detecting the lubricant used in the sliding bearing; the sliding bearing temperature data includes bearing temperature data.

[0135] The second data division module splits the second data set according to the working trajectory to obtain a plurality of second data subsets; the second data subsets include operation data subsets, lubrication data subsets, and temperature data subsets.

[0136] The second data set is divided into second data subsets by the method of splitting the first data set into first data subsets in Mine A; the division of the second data set is shown in Table 2.

[0137] Table 2 Second Dataset Partition Results Table of Mine A

[0138]

[0139] The first data subset and the second data subset correspond to each other one by one in time.

[0140] The second data recognition module constructs a bearing anomaly recognition model to recognize the second data subset. By running the data subset, lubrication data subset, and temperature data subset, bearing anomaly data is recognized.

[0141] The bearing anomaly recognition model includes an operation anomaly recognition layer, a lubrication anomaly recognition layer, and a temperature anomaly recognition layer;

[0142] The operation anomaly recognition layer is used to recognize the operation data subset. By means of the bearing vibration frequency subset, bearing amplitude subset, bearing sound subset, and bearing speed subset therein, operation anomaly data is recognized;

[0143] The lubrication anomaly recognition layer is used to recognize the lubrication data subset. By means of the lubricant viscosity subset, lubricant color subset, and lubricant texture subset therein, lubrication anomaly data is recognized;

[0144] The temperature anomaly recognition layer is used to recognize the temperature data subset to obtain temperature anomaly data;

[0145] Bearing anomaly data is obtained based on the operation anomaly data, lubrication anomaly data, and temperature anomaly data.

[0146] The present invention constructs a bearing anomaly recognition model to recognize the second data subset. By using the operation anomaly recognition layer to recognize the operation data subset, operation anomaly data is obtained; by using the lubrication anomaly recognition layer to recognize the lubrication data subset, lubrication anomaly data is obtained; by using the temperature anomaly recognition layer to recognize the temperature data subset, temperature anomaly data is obtained; and bearing anomaly data is obtained based on the operation anomaly data, lubrication anomaly data, and temperature anomaly data, so as to accurately recognize the operation condition of the sliding bearing.

[0147] The anomaly recognition module integrates the processing anomaly data and the bearing anomaly data to obtain a detection dataset; constructs a reliability recognition model, and recognizes the detection dataset through the reliability recognition model to obtain a reliability coefficient; and performs anomaly recognition and early warning of the sliding bearing through the reliability coefficient.

[0148] The acquisition and recognition process of the detection dataset is as follows:

[0149] Divide the first data set and the second data set respectively according to the working trajectory of the jaw crusher to obtain a first data subset and a second data subset;

[0150] Identify the machining anomaly data from the first data subset through the machining anomaly recognition model; identify the bearing anomaly data from the second data subset through the bearing anomaly recognition model;

[0151] Obtain the corresponding machining anomaly data and bearing anomaly data according to the working trajectory of the jaw crusher as the detection data subset;

[0152] Obtain all the detection data subsets and arrange them in chronological order to obtain a detection data set;

[0153] Identify the reliability coefficient by identifying the detection data set through the reliability recognition model.

[0154] The present invention monitors the jaw crusher to obtain a first data set; monitors the sliding bearing to obtain a second data set; splits the first data set and the second data set according to the working trajectory of the jaw crusher to obtain a first data subset and a second data subset; constructs a machining anomaly recognition model to identify the machining anomaly data from the first data subset; constructs a bearing anomaly recognition model to identify the bearing anomaly data from the second data subset; obtains a detection data set through the machining anomaly data and the bearing anomaly data; constructs a reliability recognition model to identify the detection data set to obtain the reliability coefficient, and accurately identifies and warns the reliability of the sliding bearing.

[0155] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A reliability optimization method for a sliding bearing used in a crusher, characterized in that, Including: S10. Monitor the jaw crusher during operation to obtain a first data set; the first data set includes material parameters, equipment parameters, material input data, and material output data; The jaw crusher includes a housing, jaw plates, and an eccentric shaft; among them, the housing is the structural part that bears the entire equipment; the jaw plates include a fixed jaw plate and a movable jaw plate; the eccentric shaft includes a sliding bearing; S20. Obtain the working trajectory of the jaw crusher, and split the first data set according to the working trajectory to obtain multiple first data subsets; the first data subsets include a material parameter subset, an equipment parameter subset, a material input subset, and a material output subset; S30. Build a processing anomaly recognition model to recognize the first data subset, and identify the processing anomaly data through the data of material input and material output; S40. Monitor the sliding bearing during operation to obtain a second data set, the second data set includes sliding bearing operation data, sliding bearing lubrication data, and sliding bearing temperature data; S50. Split the second data set according to the working trajectory of the jaw crusher to obtain multiple second data subsets; the second data subsets include an operation data subset, a lubrication data subset, and a temperature data subset; S60. Build a bearing anomaly recognition model to recognize the second data subset, and identify the bearing anomaly data through the operation data subset, the lubrication data subset, and the temperature data subset; S70. Integrate the processing anomaly data and the bearing anomaly data to obtain a detection data set; build a reliability recognition model, recognize the detection data set through the reliability recognition model to obtain a reliability coefficient; perform anomaly recognition and early warning of the sliding bearing through the reliability coefficient.

2. The reliability optimization method for a sliding bearing used in a crusher according to claim 1, wherein: The material parameters include material hardness, material humidity, and material viscosity; the equipment parameters include cumulative operation time, rotation speed setting, vibration frequency data, and vibration amplitude data; the material input data includes material input mass, material input shape, and material input particles; the material output data includes material output mass, material output shape, and material output particles; The sliding bearing operation data includes bearing vibration frequency data, bearing amplitude data, bearing sound data, and bearing rotation speed data; the sliding bearing lubrication data includes lubricant viscosity data, lubricant color data, and lubricant texture data; the sliding bearing temperature data includes bearing temperature data.

3. The reliability optimization method for a sliding bearing used in a crusher according to claim 1, wherein: The process of splitting the first data set according to the working trajectory of the jaw crusher is as follows: Identify the movement trajectory of the reciprocating movement of the movable jaw plate during the working process of the jaw crusher; use one reciprocating movement cycle of the movable jaw plate as the identification unit; Obtain all the identification units of the jaw crusher; split the collected first data set according to the time range where the identification unit is located to obtain the first data subset.

4. The reliability optimization method for a sliding bearing used in a crusher according to claim 1, wherein: The processing anomaly recognition model includes an output prediction layer and a processing anomaly recognition layer; The output prediction layer performs recognition and prediction through the material parameter subset, equipment parameter subset, and material input subset in the first data subset to obtain a predicted output subset; the predicted output subset includes predicted output quality, predicted output shape, and predicted output particles; The processing anomaly recognition layer compares and recognizes the predicted output subset and the material output subset, and obtains processing anomaly data through data difference recognition.

5. The reliability optimization method for a sliding bearing used in a crusher according to claim 1, wherein: The bearing anomaly recognition model includes an operation anomaly recognition layer, a lubrication anomaly recognition layer, and a temperature anomaly recognition layer; The operation anomaly recognition layer is used to recognize the operation data subset, and through the bearing vibration frequency subset, bearing amplitude subset, bearing sound subset, and bearing rotation speed subset therein, recognize the operation anomaly data; The lubrication anomaly recognition layer is used to recognize the lubrication data subset, and through the lubricant viscosity subset, lubricant color subset, and lubricant texture subset therein, recognize the lubrication anomaly data; The temperature anomaly recognition layer is used to recognize the temperature data subset to obtain temperature anomaly data; Bearing anomaly data is obtained based on the operation anomaly data, lubrication anomaly data, and temperature anomaly data.

6. The reliability optimization method for a sliding bearing used in a crusher according to claim 1, wherein: The process of obtaining and recognizing the detection data set is as follows: The first data set and the second data set are respectively divided through the working trajectory of the jaw crusher to obtain a first data subset and a second data subset; The processing anomaly data is recognized from the first data subset through the processing anomaly recognition model; the bearing anomaly data is recognized from the second data subset through the bearing anomaly recognition model; The corresponding processing anomaly data and bearing anomaly data are obtained according to the working trajectory of the jaw crusher as the detection data subset; All the detection data subsets are obtained and arranged in chronological order to obtain the detection data set; The reliability coefficient is obtained by recognizing the detection data set through the reliability recognition model.

7. A reliability optimization system for a sliding bearing used in a crusher, characterized in that, Including: The first data acquisition module monitors the working jaw crusher to obtain the first data set; the first data set includes material parameters, equipment parameters, material input data, and material output data; The first data division module obtains the working trajectory of the jaw crusher and splits the first data set according to the working trajectory to obtain a plurality of first data subsets; the first data subsets include a material parameter subset, an equipment parameter subset, a material input subset, and a material output subset; The first data recognition module constructs a processing anomaly recognition model to recognize the first data subset, and recognizes the processing anomaly data through the data of material input and material output; The second data acquisition module monitors the sliding bearing during operation to obtain a second data set, where the second data set includes sliding bearing operation data, sliding bearing lubrication data, and sliding bearing temperature data; The second data partitioning module splits the second data set according to the working trajectory to obtain multiple second data subsets; the second data subsets include an operation data subset, a lubrication data subset, and a temperature data subset; The second data identification module constructs a bearing anomaly identification model to identify the second data subsets, and through the operation data subset, the lubrication data subset, and the temperature data subset, identifies bearing anomaly data; The anomaly identification module integrates the processed anomaly data and the bearing anomaly data to obtain a detection data set; constructs a reliability identification model, identifies the detection data set through the reliability identification model to obtain a reliability coefficient; and performs anomaly identification and warning of the sliding bearing through the reliability coefficient.

8. The reliability optimization system for a sliding bearing used in a crusher according to claim 7, wherein: The process of splitting the first data set according to the working trajectory of the jaw crusher is as follows: Identify the movement trajectory of the reciprocating movement of the movable jaw plate during the working process of the jaw crusher; use one reciprocating movement cycle of the movable jaw plate as the identification unit; Obtain all the identification units of the jaw crusher; split the collected first data set according to the time range where the identification units are located to obtain first data subsets.

9. The reliability optimization system for a sliding bearing used in a crusher according to claim 7, wherein: The processed anomaly identification model includes an output prediction layer and a processed anomaly identification layer; The output prediction layer performs identification and prediction through the material parameter subset, the equipment parameter subset, and the material input subset in the first data subset to obtain a predicted output subset; the predicted output subset includes predicted output quality, predicted output shape, and predicted output particles; The processed anomaly identification layer performs comparative identification on the predicted output subset and the material output subset, and identifies processed anomaly data through data difference identification.

10. The reliability optimization system for a sliding bearing used in a crusher according to claim 7, wherein: The bearing anomaly identification model includes an operation anomaly identification layer, a lubrication anomaly identification layer, and a temperature anomaly identification layer; The operation anomaly identification layer is used to identify the operation data subset, and through the bearing vibration frequency subset, the bearing amplitude subset, the bearing sound subset, and the bearing speed subset therein, identifies operation anomaly data; The lubrication anomaly identification layer is used to identify the lubrication data subset, and through the lubricant viscosity subset, the lubricant color subset, and the lubricant texture subset therein, identifies lubrication anomaly data; The temperature anomaly identification layer is used to identify the temperature data subset to obtain temperature anomaly data; Obtain bearing anomaly data based on the operation anomaly data, the lubrication anomaly data, and the temperature anomaly data.

Images