Intelligent crusher discharge port automatic adjusting system based on machine learning algorithm

Abstract

The application discloses an intelligent crusher discharge port automatic adjusting system based on a machine learning algorithm, and sets a machine learning model module, wherein the steps are as follows: step 1, multi-source data acquisition; step 2, construction of a particle size distribution-discharge port model; step 3, establishment of a neural network correction module; step 4, input of the same input into the particle size distribution-discharge port model and the neural network correction module simultaneously; step 5, addition of a preliminarily predicted discharge particle size distribution and a neural network predicted correction amount, so as to obtain a final accurate discharge particle size distribution; and step 6, automatic adjustment of the size of the discharge port according to the final accurate discharge particle size distribution, the output of the model and the equipment state information. The application establishes a mathematical model of the crushing particle size and the size of the discharge port through the machine learning algorithm, realizes real-time adjustment of the size of the discharge port according to the material characteristics and the crushing effect, and improves the adjusting precision.

Description

Technical Field

[0001] This invention relates to an intelligent automatic adjustment system for the discharge port of a crusher based on machine learning algorithms. Background Technology

[0002] Generally, a complete set of sand making equipment includes a jaw crusher, a cone crusher, and a sand making machine.

[0003] When testing the sand-making effect of a sand making machine, a small amount of stone is usually put in first. Finally, the staff will check the sand output and particle size in the powder hopper to judge the sand-making effect of the machine. If the sand output and particle size do not meet the standards, the staff will adjust the cone crusher and the sand making machine (including adjusting the discharge port size of the cone crusher, the rotor speed of the sand making machine, or adjusting the gap between the two rollers of the roller crusher). After the staff finishes the adjustment, a small amount of stone is put in again, and the sand output and particle size are checked again, and so on.

[0004] Because it takes a long time for stone to be crushed into powder through cone crusher, vibrating screen and sand making machine, the testing cycle also needs to be long, which greatly increases the testing cost and wastes a lot of raw materials.

[0005] Therefore, in daily operation, one of the factors affecting the output of a cone crusher is the adjustment of the discharge opening. Operators must be proficient in adjusting the size of the discharge opening to ensure smooth production and that the particle size of the finished aggregate produced by the discharge opening meets the requirements. Different discharge opening sizes of cone crushers produce finished aggregates with different particle sizes.

[0006] CN114768922A discloses a method, device, and readable medium for intelligent adjustment of the discharge port size of a cone crusher. In this scheme, a cone crusher discharge port size prediction model is constructed. The predicted discharge port size is compared with a cone crusher discharge port size threshold. Based on the comparison result, an adjustment command is obtained and sent to the fixed cone assembly control system, which then adjusts the cone crusher discharge port size. However, in this scheme, the input model is an image of the finished aggregate, and parameters such as aggregate particle size, aggregate gradation curve area difference, aggregate needle-likeness, and aggregate number are analyzed based on the aggregate image.

[0007] In other words, in the above scheme, the input is only an image. However, due to the harsh environment, the image analysis is difficult and the accuracy is low, resulting in inaccurate prediction results. Summary of the Invention

[0008] The technical problem to be solved by this invention is: 1) The technical problem of low adjustment accuracy, which makes it impossible to adjust the size of the discharge port in real time according to the material characteristics and crushing effect; 2) The technical problem of lacking intelligent decision-making ability and being unable to optimize and adjust according to the operating status of the crusher and the characteristics of the material; 3) Technical problems such as poor system stability and robustness, making it susceptible to environmental factors and equipment failures; 4) The lack of remote monitoring and diagnostic capabilities hinders equipment maintenance and management. Therefore, an intelligent automatic adjustment system for the discharge port of a crusher based on machine learning algorithms is provided.

[0009] To solve the above problems, the present invention is achieved through the following technical solution: An intelligent crusher discharge port automatic adjustment system based on machine learning algorithms includes an intelligent crusher system, a data acquisition module in the intelligent crusher system connected to a controller, a machine learning model module set in the controller, and the machine learning model module connected to the discharge port adjustment module. The intelligent crushing system includes a jaw crusher with a feeder at its inlet. The jaw crusher's outlet is connected to a cone crusher, which in turn connects to a primary vibrating screen. The primary vibrating screen's first outlet is connected to a powder hopper, its second outlet to a secondary vibrating screen, and its third outlet to a sand making machine via a first conveying mechanism. The sand making machine's outlet is connected to the secondary vibrating screen via a discharge conveying mechanism, and its outlet to a powder hopper. The secondary vibrating screen's first outlet is connected to the powder hopper, its second outlet to a second silo, and its third outlet to the sand making machine via a second conveying mechanism. Monitoring equipment is installed on both the first and second conveying mechanisms. The monitoring equipment consists of a weighing device and an image particle size analyzer, both of which are connected to the controller. In the machine learning model module, perform the following processing: Step 1: Multi-source data acquisition: Data is transmitted to the machine learning model module through the weighing device and image particle size analyzer in the intelligent crusher system; Multi-source data includes: ① In the intelligent crusher system, a material detection device is set up before the feeder feeds the material to obtain physical parameters such as particle size and hardness of the material before feeding. ② Weighing devices and image particle size analyzers on the first and second conveying mechanisms are used to obtain the particle size distribution of the material after the initial crushing and multiple crushings. ③ The discharge port size of the cone crusher; Step 2: Construct a particle size distribution-discharge port model: P = (BS + I - S)f; Where P is the discharge particle size distribution matrix, B is the fragmentation distribution function matrix, S is the fragmentation probability function matrix, I is the identity matrix, and f is the feed particle size distribution matrix; Step 3: Establish a neural network correction module; Step 4: Simultaneously feed the same input into the particle size distribution-discharge port model and the neural network correction module; the particle size distribution-discharge port model obtains the preliminary predicted discharge particle size distribution; the neural network correction module obtains the correction amount Δ. P ; Step 5: Add the preliminary predicted discharge particle size distribution to the correction amount predicted by the neural network to obtain the final accurate discharge particle size distribution; Step 6: Based on the final accurate discharge particle size distribution, the controller automatically adjusts the discharge port size according to the model output and equipment status information, and realizes remote monitoring and control.

[0010] Step 3 specifically includes: Step 3.1: Construct a CNN feature extraction network to obtain feature maps. F img ; Step 3.2: Perform global average pooling to transform the feature map. F img Spatial dimension flattening yields image feature vectors. V img ; Step 3.3: Feature Fusion: Step A: Pass the numerical features through a fully connected layer to increase their dimensionality to the same level as the image features, resulting in... V gap ; Step B: Calculate the fusion vector V fused : V fused = V img ×σ( V gap ); Where σ is the Sigmoid activation function; Step 3.4: Input the fused features into the fully connected layer stack, and output the discharge port correction amount Δ. P .

[0011] Both jaw crushers and cone crushers are equipped with condition monitoring modules, which include vibration sensors and temperature sensors to monitor the vibration and temperature changes of the crushers in real time. The equipment status information and particle size data are then input into the machine learning model.

[0012] The controller is connected to an alarm device, which is a buzzer.

[0013] The second outlet of the primary vibrating screen is connected to the first silo, and the first silo is then connected to the secondary vibrating screen via a conveying mechanism.

[0014] The secondary vibrating screen is also connected to a third hopper.

[0015] It also includes step 7: The condition monitoring module monitors the vibration and temperature changes of the crusher in real time, and inputs the equipment condition information into the machine learning model, specifically including: Step 7.1: Collect the discharge port size of the current cone crusher. d The temperature T and vibration amplitude A of the cone fracture; Step 7.2: When temperature T > T 高 , and A>A 幅 If the equipment experiences abnormal and severe vibration or a sharp rise in bearing temperature, the cone crusher should be stopped for inspection. Among them, T 高 The highest rated value T of the cone crusher 高 A 幅 The maximum vibration amplitude A of the cone fracture. 幅 The unit is millimeters per second; Step 7.3: When T 均 <T<T 高 At that time, ΔT = |T – T 均 If ΔT increases by 0.5℃, then the discharge port size will... d Increase by 1mm; When A 均 <A<A 幅 ΔA =|A – A 均 If ΔA increases by 0.2 mm / s, then the discharge port size will change. d Increase by 1mm; Among them, T 均 A represents the average temperature value during normal operation of the cone crusher. 均 This is the average vibration amplitude threshold when the cone crusher is operating normally.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. Improve adjustment accuracy: By establishing a mathematical model of crushing particle size and discharge port size through machine learning algorithms, the discharge port size can be adjusted in real time according to material characteristics and crushing effect, thereby improving adjustment accuracy.

[0017] 2. Enhance intelligent decision-making capabilities: Utilize deep learning algorithms and transfer learning techniques to improve the accuracy and adaptability of the model, enabling the system to optimize and adjust according to the crusher's operating status and material characteristics.

[0018] 3. Improve system stability and robustness: Adaptive learning rate optimization algorithms and momentum terms are employed to reduce oscillations during model training and improve model stability. Simultaneously, multi-sensor fusion and state monitoring provide early warnings of equipment anomalies, preventing equipment failures from affecting the fragmentation scale.

[0019] 4. Enable remote monitoring and diagnostics: Develop an intelligent control system that integrates sensors, machine learning models, and discharge port adjustment devices. It features automatic diagnostics, intelligent decision-making, and remote control functions, allowing operators to manage and maintain the equipment from different locations. Attached Figure Description

[0020] Figure 1 This is an overall structural diagram of the present invention; Figure 2 This is a flowchart of the present invention; Figure 3 This is a flowchart of the intelligent closed-loop adjustment process for the discharge port. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] In the description of this invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0023] An intelligent crusher discharge port automatic adjustment system based on machine learning algorithms includes an intelligent crusher system, a data acquisition module in the intelligent crusher system connected to a controller, a machine learning model module set in the controller, and the machine learning model module connected to the discharge port adjustment module.

[0024] like Figure 1As shown, the intelligent crushing system includes a jaw crusher 1, a feeder 2 at the inlet of the jaw crusher 1, a cone crusher 3 at the outlet of the jaw crusher 1, a primary vibrating screen 4 at the outlet of the cone crusher 3, a powder hopper 6 at the first outlet of the primary vibrating screen 4, a secondary vibrating screen 5 at the second outlet of the primary vibrating screen 4, a sand making machine 10 at the third outlet of the primary vibrating screen 4 via a first conveying mechanism 11, a secondary vibrating screen 5 at the outlet of the sand making machine 10 via a discharge conveying mechanism 13, and a powder hopper at the outlet of the secondary vibrating screen 5.

[0025] A monitoring device, specifically a weighing device, is installed on the first conveying mechanism 11. More preferably, the monitoring device also includes an image particle size analyzer. Both the weighing device and the image particle size analyzer are connected to a controller, which is connected to an alarm device, such as a buzzer. This allows for the setting of a weight threshold within the controller. When the real-time weight detected by the weighing device falls below the weight threshold, the controller outputs a signal to the alarm device, thus reminding the operator to adjust the discharge port size of the cone crusher.

[0026] Better yet, the second outlet of the primary vibrating screen 4 is connected to the first silo 7, and the first silo 7 is then connected to the secondary vibrating screen 5 via a conveying mechanism.

[0027] Even better, the first outlet of the secondary vibrating screen 5 is connected to the powder hopper 6, the second outlet of the secondary vibrating screen 5 is connected to the second silo 8, and the third outlet of the secondary vibrating screen 5 is connected to the sand making machine 10 via the second conveying mechanism 12. Monitoring equipment, including an image particle size analyzer and a weighing device, is also installed on the second conveying mechanism 12.

[0028] Even better, the secondary vibrating screen 5 is also connected to a third hopper 9.

[0029] Even better, both the jaw crusher 1 and the cone crusher 3 are equipped with a status monitoring module. The status monitoring module includes a vibration sensor and a temperature sensor to monitor the vibration and temperature changes of the crusher in real time. The equipment status information and particle size data are input into the machine learning model. This allows the data from these sensors to be fused and processed. The data fusion algorithm is used to comprehensively analyze the operating status of the equipment and the characteristics of the material, enabling the machine learning model to make more comprehensive and accurate decisions on adjusting the size of the discharge port.

[0030] like Figure 2 , Figure 3 As shown, the following processing is performed in the machine learning model module: Step 1: Multi-source data acquisition: The weighing device and image particle size analyzer in the intelligent crusher system transmit data to the machine learning model module.

[0031] Multi-source data includes: ① In the intelligent crusher system, a material detection device is set up before the feeder 2 feeds the material to obtain physical parameters such as particle size and hardness of the material before feeding. ② Weighing devices and image particle size analyzers on the first conveying mechanism 11 and the second conveying mechanism 12 are used to obtain the particle size distribution of the material after the initial crushing and multiple crushing. ③ The discharge port size of cone crusher 3; ④ Better still, it also includes the state parameters of the jaw crusher 1 and the cone crusher 3: vibration values ​​(amplitude, acceleration or velocity) and temperature values.

[0032] Step 2: Construct a particle size distribution-discharge port model: P = (BS + I - S)f; Where P is the discharge particle size distribution matrix, I is the identity matrix, f is the feed particle size distribution matrix, B is the fragmentation distribution function matrix, which indicates the probability that a particle of a certain size will be broken; and S is the fragmentation probability function matrix, which indicates the proportion of each small particle after a large particle is broken.

[0033] Step 3: Establish a neural network correction module; Step 3.1: Construct a CNN feature extraction network, preferably a lightweight network such as ResNet-18 or MobileNet; obtain feature maps through the CNN feature extraction network. F img ; Step 3.2: Perform global average pooling (GAP) on the feature map. F img Spatial dimension flattening yields image feature vectors. V img ; Step 3.3: Feature Fusion: Step A: Pass the numerical features through a fully connected layer to increase their dimensionality to the same level as the image features, resulting in... V gap ; Step B: Calculate the fusion vector V fused : V fused = V img ×σ( V gap ); Where σ is the Sigmoid activation function.

[0034] Step 3.4: Input the fused features into the fully connected layer stack, and output the discharge port correction amount Δ. P .

[0035] Step 4: Input the same data (feed particle size and discharge port size) simultaneously into the particle size distribution-discharge port model and the neural network correction module; the particle size distribution-discharge port model obtains the preliminary predicted discharge particle size distribution; the neural network correction module obtains the correction amount Δ. P Thus, the task of the neural network is not to predict the granularity from scratch, but to learn the prediction error of the mechanism model, that is, the difference between the true distribution and the initial prediction of the distribution by the mechanism model.

[0036] Neural networks only need to learn "residuals" or "corrections," which greatly reduces the learning difficulty and improves the model's accuracy and generalization ability.

[0037] Step 5: Add the preliminary predicted discharge particle size distribution to the correction amount predicted by the neural network to obtain the final accurate discharge particle size distribution.

[0038] Step 6: Based on the final accurate discharge particle size distribution, the controller outputs a control signal to the discharge port adjustment module according to the model output and equipment status information. The discharge port adjustment module automatically adjusts the discharge port size. Simultaneously, the controller continuously performs remote monitoring and control. Even better, the weighing device and image particle size analyzer continuously monitor the particle size of the discharged material and feed the data back to the machine learning model.

[0039] Furthermore, it also includes step 7: the status monitoring module monitors the vibration and temperature changes of the crusher in real time and inputs the equipment status information into the machine learning model.

[0040] When the discharge port is reduced in size, the crushing chamber becomes narrower, increasing the resistance to material flow and inevitably increasing the equipment load. The most direct consequence is that bearings and other friction pairs generate more heat, leading to higher oil temperatures or greater vibration. Therefore, vibration and temperature changes are key indicators for monitoring the appropriateness of the discharge port adjustment.

[0041] Therefore, step 7 includes: Step 7.1: Collect the discharge port size of the current cone crusher 3. d The temperature T and vibration amplitude A of the cone fracture 3; Step 7.2: When temperature T > T 高 , and A>A 幅 When abnormal and severe vibrations occur in the equipment or the bearing temperature rises sharply, the cone crusher should be stopped for inspection. Among them, T 高 The highest rated value T for the cone crusher 3 高 A 幅 The maximum vibration amplitude A of the cone fracture 3. 幅 The unit is millimeters per second (mm / s); Step 7.3: When T 均 <T<T 高 At that time, ΔT = |T – T 均 If ΔT increases by 0.5℃, then the discharge port size will... d Increase by 1mm; When A 均 <A<A 幅 ΔA =|A – A 均 If ΔA increases by 0.2 mm / s, then the discharge port size will change. d Increase by 1mm.

[0042] Among them, T 均 A is the average temperature value of the cone crusher 3 during normal operation. 均 This is the average vibration amplitude threshold when the cone crusher 3 is working normally.

[0043] The purpose of the discharge port adjustment module in this invention is to change the distance between the bottom of the moving jaw plate and the fixed jaw plate. Specifically, the discharge port adjustment module includes a hydraulic cylinder connected to a controller. The piston rod of the hydraulic cylinder is connected to the lower part of the moving jaw, and the size of the discharge port is directly changed by extending and retracting the piston through the hydraulic system.

[0044] The discharge port adjustment module can also adopt a wedge-hydraulic composite type, such as CN206343207U. The hydraulic cylinder changes the stacking thickness of the wedges, thereby pushing the position of the toggle plate and the moving jaw to achieve rapid adjustment of the discharge port. This design is easy to adjust and usually has a mechanical locking mechanism. During operation, the impact pressure is borne by the pad or wedge, and the hydraulic system is not subjected to stress for a long time, making it more stable and reliable.

[0045] Compared with existing technologies, the beneficial effects of this technical solution are as follows: 1. Improve adjustment accuracy: By establishing a mathematical model of crushing particle size and discharge port size through machine learning algorithms, the discharge port size can be adjusted in real time according to material characteristics and crushing effect, thereby improving adjustment accuracy.

[0046] 2. Enhance intelligent decision-making capabilities: Utilize deep learning algorithms and transfer learning techniques to improve the accuracy and adaptability of the model, enabling the system to optimize and adjust according to the crusher's operating status and material characteristics.

[0047] 3. Improve system stability and robustness: Adaptive learning rate optimization algorithms and momentum terms are employed to reduce oscillations during model training and improve model stability. Simultaneously, multi-sensor fusion and state monitoring provide early warnings of equipment anomalies, preventing equipment failures from affecting the fragmentation scale.

[0048] 4. Enable remote monitoring and diagnostics: Develop an intelligent control system that integrates sensors, machine learning models, and discharge port adjustment devices. It features automatic diagnostics, intelligent decision-making, and remote control functions, allowing operators to manage and maintain the equipment from different locations.

[0049] The above description is only a preferred embodiment of the present invention. It should be noted that those skilled in the art can make several changes and improvements without departing from the overall concept of the present invention, and these should also be considered within the scope of protection of the present invention.

Claims

1. An intelligent automatic discharge port adjustment system for a crusher based on machine learning algorithms, characterized in that: It includes an intelligent crusher system, in which the data acquisition module is connected to the controller, and a machine learning model module is set in the controller, which is connected to the discharge port adjustment module. The intelligent crushing system includes a jaw crusher (1), a feeder (2) is provided at the inlet of the jaw crusher (1), the discharge end of the jaw crusher (1) is connected to a cone crusher (3), the discharge port of the cone crusher (3) is connected to a primary vibrating screen (4), the first outlet of the primary vibrating screen (4) is connected to a powder hopper (6), the second outlet of the primary vibrating screen (4) is connected to a secondary vibrating screen (5), the third outlet of the primary vibrating screen (4) is connected to a sand making machine (10) through a first conveying mechanism (11), the discharge port of the sand making machine (10) is connected to the secondary vibrating screen (5) through a discharge conveying mechanism (13), and the discharge port of the secondary vibrating screen (5) is connected to a powder hopper; the first outlet of the secondary vibrating screen (5) is connected to a powder hopper (6), the second outlet of the secondary vibrating screen (5) is connected to a second silo (8), and the third outlet of the secondary vibrating screen (5) is connected to the sand making machine (10) through a second conveying mechanism (12). Monitoring equipment is provided on both the first conveying mechanism (11) and the second conveying mechanism (12). The monitoring equipment is a weighing device and an image particle size analyzer. Both the weighing device and the image particle size analyzer are connected to the controller. In the machine learning model module, perform the following processing: Step 1: Multi-source data acquisition: Data is transmitted to the machine learning model module through the weighing device and image particle size analyzer in the intelligent crusher system; Multi-source data includes: ① In the intelligent crusher system, a material detection device is set up before the feeder (2) feeds the material to obtain physical parameters such as particle size and hardness of the material before feeding. ② Weighing devices and image particle size analyzers on the first conveying mechanism (11) and the second conveying mechanism (12) are used to obtain the particle size distribution of the material after the initial crushing and multiple crushings. ③ The discharge port size of the cone crusher (3); Step 2: Construct a particle size distribution-discharge port model: P = (BS + I - S)f; Where P is the discharge particle size distribution matrix, B is the fragmentation distribution function matrix, S is the fragmentation probability function matrix, I is the identity matrix, and f is the feed particle size distribution matrix; Step 3: Establish a neural network correction module; Step 4: Simultaneously feed the same input into the particle size distribution-discharge port model and the neural network correction module; the particle size distribution-discharge port model obtains the preliminary predicted discharge particle size distribution; the neural network correction module obtains the correction amount Δ. P ; Step 5: Add the preliminary predicted discharge particle size distribution to the correction amount predicted by the neural network to obtain the final accurate discharge particle size distribution; Step 6: Based on the final accurate discharge particle size distribution, the controller automatically adjusts the discharge port size according to the model output and equipment status information, and realizes remote monitoring and control.

2. The intelligent crusher discharge port automatic adjustment system based on machine learning algorithm according to claim 1, characterized in that: Step 3 specifically includes: Step 3.1: Construct a CNN feature extraction network to obtain feature maps. F img ; Step 3.2: Perform global average pooling to transform the feature map. F img Spatial dimension flattening yields image feature vectors. V img ; Step 3.3: Feature Fusion: Step A: Pass the numerical features through a fully connected layer to increase their dimensionality to the same level as the image features, resulting in... V gap ; Step B: Calculate the fusion vector V fused : V fused = V img ×σ( V gap ); Where σ is the Sigmoid activation function; Step 3.4: Input the fused features into the fully connected layer stack, and output the discharge port correction amount Δ. P .

3. The intelligent crusher discharge port automatic adjustment system based on machine learning algorithm according to claim 1, characterized in that: A status monitoring module is installed on both the jaw crusher (1) and the cone crusher (3). The status monitoring module includes a vibration sensor and a temperature sensor to monitor the vibration and temperature changes of the crusher in real time and input the equipment status information and particle size data into the machine learning model.

4. The intelligent crusher discharge port automatic adjustment system based on machine learning algorithm according to claim 1, characterized in that: The controller is connected to an alarm device, which is a buzzer.

5. The intelligent crusher discharge port automatic adjustment system based on machine learning algorithm according to claim 1, characterized in that: The second outlet of the primary vibrating screen (4) is connected to the first silo (7), and the first silo (7) is then connected to the secondary vibrating screen (5) through a conveying mechanism.

6. The intelligent crusher discharge port automatic adjustment system based on machine learning algorithm according to claim 5, characterized in that: The secondary vibrating screen (5) is also connected to a third silo (9).

7. The intelligent crusher discharge port automatic adjustment system based on machine learning algorithm according to claim 1, characterized in that: It also includes step 7: The condition monitoring module monitors the vibration and temperature changes of the crusher in real time, and inputs the equipment condition information into the machine learning model, specifically including: Step 7.1: Collect the discharge port size of the current cone crusher (3) d The temperature T and vibration amplitude A of the cone crusher (3); Step 7.2: When temperature T > T 高 , and A>A 幅 When the equipment experiences abnormal and severe vibrations or the bearing temperature rises sharply, the cone crusher (3) should be stopped for inspection. Among them, T 高 The highest rated value T of the cone crusher (3) 高 A 幅 The maximum vibration amplitude A of the conical fracture (3) 幅 The unit is millimeters per second (mm / s); Step 7.3: When T 均 <T<T 高 At that time, ΔT = |T – T 均 If ΔT increases by 0.5℃, then the discharge port size will... d Increase by 1mm; When A 均 <A<A 幅 ΔA =|A – A 均 If ΔA increases by 0.2 mm / s, then the discharge port size will change. d Increase by 1mm; Among them, T 均 A is the average temperature value when the cone crusher (3) is working normally. 均 The average vibration amplitude threshold of the cone crusher (3) during normal operation.

Images