Power plant material conveying device based on permanent magnet roller driving and conveying method

Abstract

The invention belongs to the technical field of material conveying, and discloses a power plant material conveying device and conveying method.The power plant material conveying device comprises a rack, permanent magnet rollers, a conveying belt, a driving motor, a feeding hopper and a cleaning mechanism, and the permanent magnet rollers are rotationally installed at the two ends of the rack; the conveying belt is arranged on the surface of the permanent magnet roller and used for conveying materials, an output shaft of a driving motor is connected with the permanent magnet roller and used for driving the permanent magnet roller to rotate, and a feeding hopper is arranged on the rack and located at one end above the conveying belt; the cleaning mechanism is arranged at the tail end of the conveying belt and used for cleaning the surface of the conveying belt. Through the arrangement of the first cleaning assembly and the second cleaning assembly, the first cleaning assembly and the second cleaning assembly which are arranged in a staggered mode can be used for conducting reciprocating motion, the conveying belt is effectively cleaned, cleaning dead corners are avoided, material residues are avoided, and it is guaranteed that the surface of the conveying belt is clean and tidy.

Description

Technical Field

[0001] The invention belongs to the technical field of material conveying, and in particular relates to a material conveying device and a conveying method for a power plant based on permanent magnetic roller drive. Background Art

[0002] In modern power plants, material conveying devices are key equipment to ensure the smooth transportation of fuel, raw materials and other materials. Permanent magnet roller drive technology is a new driving method that uses a permanent magnet synchronous motor to directly drive the roller and realizes material transportation through the friction between the roller and the conveyor belt.

[0003] For example, the Chinese patent with publication number CN116495518A discloses a material conveying device, including a feeding hopper, a conveyor belt, a paving unit, a conveying assembly, a toggle unit and a reset unit. The conveying frame is divided into a horizontal section and an inclined section extending along the rear upper side direction. The paving unit includes two guide plates sliding along the width direction of the conveyor frame. The conveying assembly includes a baffle arranged along the width direction of the conveyor belt, and the baffle is arranged on the conveyor belt and is located below the guide plate. The invention presses the baffle through two guide plates, so that a storage space is formed between the baffle and the two baffles. The width of the storage space is controlled by the flow rate of the material discharged from the feeding hopper to ensure that the thickness of the material in the storage space is constant, so as to avoid the situation that the material is scorched by the drying box due to the material thickness being too thin when the material passes through the dryer, or the material is not completely dried due to the material thickness being too large.

[0004] The above patents also have the following problems:

[0005] When using a conveyor to transport materials, the weight, distribution and humidity of the materials on the conveyor belt are different. These factors will affect the load of the conveyor and thus affect the conveying speed of the conveyor. When conveying materials, existing conveyors cannot adaptively adjust the conveying speed based on the characteristics of the materials themselves and their distribution on the conveyor belt, which may easily lead to problems such as material pile-up and leakage, thereby affecting the stable transportation of materials. Moreover, when monitoring their own working conditions, existing conveyors mostly use real-time monitoring, which cannot provide early warnings and have a certain lag, which may easily lead to downtime and production losses caused by sudden equipment failures, affecting production efficiency and requiring improvement. Summary of the invention

[0006] The object of the present invention is to provide a material conveying device and a conveying method for a power plant based on a permanent magnet roller drive, so as to solve the technical problems raised in the existing background technology.

[0007] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a material conveying device for a power plant driven by a permanent magnetic roller, comprising: a frame; a permanent magnetic roller, rotatably mounted at both ends of the frame; a conveying belt, arranged on the surface of the permanent magnetic roller, for conveying materials; a cleaning mechanism, arranged at the end of the conveying belt, for cleaning the surface of the conveying belt; a control system;

[0008] The cleaning mechanism comprises a first cleaning component and a second cleaning component, the first cleaning component and the second cleaning component have the same structure and are relatively staggered;

[0009] The control system comprises:

[0010] A data collection module, used to collect a historical training data set of the transmission device, wherein the historical training data set includes a transmission comprehensive influencing parameter and a transmission speed;

[0011] The speed prediction module is used to train a machine learning model for predicting the transmission speed based on the comprehensive transmission influencing parameters, collect real-time comprehensive transmission influencing parameters, and predict the transmission speed based on the trained machine learning model.

[0012] Preferably, the control system further comprises:

[0013] A data acquisition module is used to acquire historical transmission data of the transmission device, the historical transmission data includes transmission device influencing parameters and a transmission parameter change set, and convert the transmission parameter change set into a transmission parameter change number, the transmission parameter change number is i=1, 2, 3....n, and n represents the total number of transmission parameter change numbers;

[0014] The parameter prediction module trains a machine learning model for predicting the transmission parameter change number at a future moment based on the transmission device influencing parameters, and then obtains the transmission parameter change set corresponding to the transmission parameter change number;

[0015] The data analysis module generates a device stability coefficient based on the predicted set of transmission parameter changes at future moments, and generates a comprehensive evaluation result based on the device stability coefficient. The comprehensive evaluation result includes a good state of the transmission device, a general state of the transmission device, and a poor state of the transmission device.

[0016] Preferably, the first cleaning component includes: a reciprocating cylinder fixedly mounted on the frame; a cleaning barrel evenly arranged on one side of the conveyor belt and in contact with the surface of the conveyor belt; and a connecting frame arranged on one side of the cleaning barrel and connected to the driving end of the reciprocating cylinder.

[0017] Preferably, the cleaning cylinder includes: a cylinder body, which is hollow inside; a fixed cavity, which is arranged on one side of the cylinder body, close to the conveyor belt, and connected to the interior of the cylinder body; exhaust holes, which are evenly distributed on one side of the fixed cavity and face the surface of the conveyor belt; a cleaning brush, which is arranged on one side of the fixed cavity and contacts the surface of the conveyor belt; and a piston rod, which is fixed on the frame and one end of which extends into the interior of the cylinder body.

[0018] Preferably, the training method of the machine learning model for predicting the transmission speed is as follows:

[0019] Converting the collected transmission comprehensive impact parameters into a corresponding set of feature vectors;

[0020] Each group of feature vectors is used as the input of the machine learning model. The machine learning model uses the transmission speed predicted by each group of transmission comprehensive influencing parameters as the output, uses the transmission speed actually corresponding to each group of transmission comprehensive influencing parameters as the prediction target, and uses minimizing the loss function value of the machine learning model as the training target; when the loss function value of the machine learning model is less than or equal to the preset target loss value, the training is stopped;

[0021] The machine learning model is one of the models such as SVM regression, random forest regression or neural network regression.

[0022] Preferably, the transmission parameter change set is (a n , b n , c n ), a, b, c correspond to the vibration, temperature and tension change rate of the conveyor respectively, a n ,b n ,c n Indicates the vibration, temperature and tension change rates of the corresponding transmission device when the transmission parameter change number is n.

[0023] Preferably, the method for predicting the transmission parameter change number at a future moment includes:

[0024] Preset the prediction time step C, sliding step Z and sliding window length L; use the sliding window method to convert the transmission device influencing parameters into multiple training samples, one training sample corresponds to a label, and constitutes a group of training data, and multiple groups of training data constitute a training set, and use the training set as the input of the machine learning model, and predict the transmission parameter change number at the future moment after the time step C as the output, and the subsequent transmission parameter change number of each training set as the prediction target, and use the prediction accuracy as the training target to train the machine learning; generate a machine learning model for predicting the transmission parameter change number at the future moment according to the transmission device influencing parameters; the machine learning model is one of support vector machine regression, random forest regression or neural network regression.

[0025] Preferably, the device stability coefficient is obtained by performing a weighted calculation on the vibration, temperature and tension change rate of the conveying device at a predicted future moment.

[0026] Preferably, the method of generating a comprehensive evaluation result according to the device stability coefficient includes:

[0027] Preset device stability coefficient gradient threshold Wx 1 With Wx 2 ,Wx 1 >Wx 2 ;

[0028] If Wx≤Wx 2 , then the comprehensive evaluation result is that the device is in good condition;

[0029] If Wx 1 ≥Wx>Wx 2 , then the comprehensive evaluation result is that the device status is general;

[0030] If Wx>Wx 1 , the comprehensive evaluation result is that the device status is poor.

[0031] The material conveying method for a power plant based on permanent magnetic roller drive is applied to the above-mentioned material conveying device for a power plant based on permanent magnetic roller drive, and comprises the following steps:

[0032] Step 1: Collect a historical training data set of the transmission device, wherein the historical training data set includes a transmission comprehensive influencing parameter and a transmission speed;

[0033] Step 2: Train a machine learning model for predicting the transmission speed based on the comprehensive transmission influencing parameters, collect the real-time comprehensive transmission influencing parameters, and predict the transmission speed based on the trained machine learning model;

[0034] Step 3: Convey the material according to the predicted conveying speed, and use the cleaning mechanism to clean the conveyor belt surface in real time;

[0035] Step 4: Acquire historical transmission data of the transmission device, the historical transmission data includes transmission device influencing parameters and a transmission parameter change set, convert the transmission parameter change set into a transmission parameter change number, the transmission parameter change number is i=1, 2, 3...n, n represents the total number of transmission parameter change numbers;

[0036] Step 5: Based on the transmission device influencing parameters, a machine learning model is trained to predict the transmission parameter change number at a future moment, and then a transmission parameter change set corresponding to the transmission parameter change number is obtained;

[0037] Step 6: Generate a device stability coefficient based on the predicted set of transmission parameter changes at future moments, and generate a comprehensive evaluation result based on the device stability coefficient. The comprehensive evaluation result includes a transmission device in good condition, a transmission device in average condition, and a transmission device in poor condition.

[0038] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0039] 1. The present invention can utilize the reciprocating motion of the relatively staggered first cleaning component and the second cleaning component by arranging the first cleaning component and the second cleaning component, and use the cleaning brush to clean the surface of the conveyor belt. At the same time, the gas is blown to the surface of the conveyor belt to be cleaned through a plurality of exhaust holes arranged on one side of the fixed cavity, so as to perform secondary cleaning. The conveyor belt can be effectively cleaned, and dead corners for cleaning and material residues can be avoided, thereby ensuring that the surface of the conveyor belt is clean.

[0040] 2. The present invention can dynamically adjust the speed of the conveyor belt according to the actual weight, distribution and humidity of the material, ensure that the material is transported at the optimal speed, optimize the conveying efficiency, and timely adjust the conveying speed to avoid the accumulation or congestion of materials on the conveyor belt, reduce production line bottlenecks, and improve overall production efficiency. It can prevent excessive overflow or falling of materials, improve the accuracy of material processing, predict the conveying speed in real time and adjust it, realize intelligent control and automatic management, reduce manual intervention, and improve the automation level of the system.

[0041] 3. The present invention can identify potential failure risks in advance by predicting future parameters such as vibration, temperature and tension change rate. Abnormal vibration, excessive temperature or excessive tension change rate may indicate that the equipment is about to fail. Early warning can arrange maintenance and repairs, thereby reducing downtime and production losses caused by sudden equipment failures; and according to the predicted stability coefficient, a maintenance plan is formulated to carry out targeted preventive maintenance, reduce sudden equipment failures, ensure the smooth operation of the production line, and improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A three-dimensional diagram of a material conveying device for a power plant driven by a permanent magnetic roller according to the present invention is shown;

[0044] Figure 2The overall structural schematic diagram of the material conveying device of a power plant driven by a permanent magnetic roller according to the present invention is shown;

[0045] Figure 3 A schematic diagram of the cleaning mechanism structure of the present invention is shown;

[0046] Figure 4 A schematic diagram of the cleaning cartridge structure of the present invention is shown;

[0047] Figure 5 A schematic diagram showing the module connection relationship of the control system of Embodiment 2 of the present invention is shown;

[0048] Figure 6 A schematic diagram showing the module connection relationship of the control system of Example 3 of the present invention is shown;

[0049] Figure 7 A flow chart of a material conveying method for a power plant based on permanent magnet drum drive according to Embodiment 4 of the present invention is shown.

[0050] Figure numerals: 100, frame; 200, permanent magnet roller; 300, conveyor belt; 400, cleaning mechanism; 401, first cleaning component; 401a, reciprocating cylinder; 401b, cleaning cylinder; 401b-1, cylinder body; 401b-2, fixed cavity; 401b-3, exhaust hole; 401b-4, cleaning brush; 401b-5, piston rod; 401c, connecting frame; 402, second cleaning component; 500, driving motor; 600, upper hopper. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] Example 1

[0053] Reference Figure 1-2As shown, a material conveying device for a power plant driven by a permanent magnetic drum comprises: a frame 100, a permanent magnetic drum 200, a conveying belt 300, a driving motor 500, an upper hopper 600 and a cleaning mechanism 400, wherein the permanent magnetic drum 200 is rotatably mounted at both ends of the frame 100; the conveying belt 300 is arranged on the surface of the permanent magnetic drum 200 for conveying materials, the output shaft of the driving motor 500 is connected to the permanent magnetic drum 200 for driving the permanent magnetic drum 200 to rotate, the upper hopper 600 is arranged on the frame 100 and is located at one end above the conveying belt 300; the cleaning mechanism 400 is arranged at the end of the conveying belt 300 for cleaning the surface of the conveying belt 300;

[0054] In this embodiment, the material to be transported can be guided onto the conveyor belt 300 through the feed hopper, and at the same time, the drive motor 500 is started to drive the permanent magnet roller 200 to rotate, thereby making the conveyor belt 300 rotate, and the conveyor belt 300 is used to transport the material from one end to the other end, and the cleaning mechanism 400 is used to clean the surface of the conveyor belt 300 to prevent the material from adhering to the surface of the conveyor belt 300 and affecting subsequent conveying work.

[0055] Specifically, refer to Figure 3 As shown, the cleaning mechanism 400 includes a first cleaning component 401 and a second cleaning component 402, the first cleaning component 401 and the second cleaning component 402 have the same structure and are relatively staggered; the first cleaning component 401 includes: a reciprocating cylinder 401a, a cleaning cylinder 401b and a connecting frame 401c, wherein the reciprocating cylinder 401a is fixedly mounted on the frame 100; there are at least three cleaning cylinders 401b, which are evenly arranged on one side of the conveyor belt 300 and contact the surface of the conveyor belt 300; the connecting frame 401c is arranged on one side of the cleaning cylinder 401b, used to connect the three cleaning cylinders 401b, and connected to the driving end of the reciprocating cylinder 401a;

[0056] In this embodiment, there are at least three cleaning cylinders 401b on the first cleaning component 401 and the second cleaning component 402, and the cleaning cylinders 401b on the first cleaning component 401 and the second cleaning component 402 are arranged alternately. The reciprocating cylinder 401a can be used to drive the cleaning cylinder 401b to reciprocate to clean the surface of the conveyor belt 300, which can avoid cleaning dead corners and ensure a good cleaning effect.

[0057] Specifically, refer to Figure 4As shown, the cleaning cylinder 401b includes: a cylinder body 401b-1, a fixed cavity 401b-2, an exhaust hole 401b-3, a cleaning brush 401b-4 and a piston rod 401b-5, wherein the cylinder body 401b-1 is provided with a cavity inside; the fixed cavity 401b-2 is provided at one side of the cylinder body 401b-1, close to the conveyor belt 300, and communicated with the inside of the cylinder body 401b-1; the exhaust holes 401b-3 are evenly distributed at one side of the fixed cavity 401b-2, and face the conveyor belt 300. The surface of the conveyor belt 300; a cleaning brush 401b-4, which is arranged on one side of the fixed cavity 401b-2 and contacts the surface of the conveyor belt 300; a piston rod 401b-5, which is fixedly arranged on the frame 100, and one end of which extends to the inside of the cylinder 401b-1, an air inlet is opened at one end of the cylinder 401b-1, an air outlet is opened on one side of the cylinder 401b-1, and the cylinder 401b-1 is connected with the inside of the fixed cavity 401b-2 through the air outlet, and a one-way valve is provided in both the air inlet and the air outlet;

[0058] In this embodiment, when the reciprocating cylinder 401a pushes the connecting frame 401c to move, it will drive the cylinder 401b-1 to move along the width direction of the conveyor belt 300, and use the cleaning brush 401b-4 on one side of the cylinder 401b-1 to clean the surface of the conveyor belt 300. At the same time, when the cylinder 401b-1 moves, one end of the piston rod 401b-5 moves toward the inside of the cylinder 401b-1, and the gas inside the cylinder 401b-1 is discharged to the inside of the fixed cavity 401b-2 through the gas outlet, and Gas is blown toward the surface of the cleaned conveyor belt 300 through multiple exhaust holes 401b-3 arranged on one side of the fixed cavity 401b-2 for secondary cleaning. The relatively staggered first cleaning component 401 and the second cleaning component 402 are used for reciprocating motion, so that the conveyor belt 300 can be effectively cleaned to avoid cleaning dead corners and material residues, thereby ensuring that the surface of the conveyor belt 300 is clean and tidy, and reducing the phenomenon of accelerated wear of the conveyor belt 300 due to material adhering to the surface of the conveyor belt 300.

[0059] Working principle: The material to be transported is guided to fall onto the conveyor belt 300 through the feed hopper, and the drive motor 500 is started to drive the permanent magnet roller 200 to rotate, thereby making the conveyor belt 300 rotate, and the conveyor belt 300 is used to transport the material from one end to the other end, and the reciprocating cylinder 401a on the first cleaning component 401 and the second cleaning component 402 is started at the same time, and the reciprocating cylinder 401a is used to push the connecting frame 401c to move, and drive the cylinder 401b-1 to move along the width direction of the conveyor belt 300, and the cleaning brush 401b-4 on one side of the cylinder 401b-1 is used to clean the surface of the conveyor belt 300, and at the same time While the cylinder 401b-1 moves, one end of the piston rod 401b-5 moves toward the inside of the cylinder 401b-1, and the gas inside the cylinder 401b-1 is discharged to the inside of the fixed chamber 401b-2 through the gas outlet, and the gas is blown toward the surface of the cleaned conveyor belt 300 through multiple exhaust holes 401b-3 arranged on one side of the fixed chamber 401b-2, for secondary cleaning. By utilizing the reciprocating motion of the relatively staggered first cleaning component 401 and the second cleaning component 402, the conveyor belt 300 can be effectively cleaned, avoiding cleaning dead corners and material residues, thereby ensuring that the surface of the conveyor belt 300 is clean.

[0060] Example 2

[0061] Reference Figure 5 As shown, the present invention further includes a control system based on Example 1, and the control system includes: a data acquisition module and a speed prediction module, and the modules are connected by wired / wireless means to realize data transmission;

[0062] A data collection module, used to collect a historical training data set of the transmission device, wherein the historical training data set includes a transmission comprehensive influencing parameter and a transmission speed;

[0063] Specifically, the comprehensive influencing parameters of transmission include the weight, distribution, humidity and tension of the conveyor belt of the conveyed material;

[0064] The weight of the conveyed material refers to the total weight of the conveyed material on the conveyor belt. The total weight of the material directly affects the load of the conveyor belt and the roller. Heavier materials will increase the load of the conveyor and require greater driving force to maintain the conveying speed. Excessive weight of the material will increase the load of the conveyor belt and the roller. The motor and the roller need to provide greater driving force, which may cause the roller speed to decrease and the conveying speed to decrease. The weight of the conveyed material can be obtained in real time through the weighing sensor;

[0065] The distribution of the conveyed material refers to whether the thickness of the conveyed material on the conveyor belt is uniform;

[0066] Specifically, the accumulation thickness of materials on the conveyor belt will affect the load of the conveyor. Uneven thickness will lead to uneven load distribution, increase the load fluctuation of the conveyor, and further increase the power consumption of the conveyor, affecting the conveying speed.

[0067] The method to judge whether the accumulation thickness of materials on the conveyor belt is uniform is as follows:

[0068] Select N sampling points evenly along the width of the conveyor belt, N = 1, 2, 3, ..., i, and record the material thickness h at each sampling point i , which can be obtained in real time through the laser ranging sensor;

[0069] Calculate the average stacking thickness:

[0070]

[0071] In the formula, Indicates the average accumulation thickness of materials on the conveyor belt;

[0072] Calculate the standard deviation of thickness:

[0073]

[0074] In the formula, σ represents the standard deviation of the thickness of the material piled on the conveyor belt;

[0075] The standard deviation σ of the material accumulation thickness on the conveyor belt can be used as an indicator to measure the uniformity of the material thickness. The smaller the standard deviation, the more uniform the material thickness; the larger the standard deviation, the more uneven the material thickness.

[0076] The humidity of the conveyed material will affect the conveying speed. High-humidity materials have poor fluidity and are easy to adhere to the conveyor belt and roller surface, increasing friction, resulting in reduced conveying efficiency and reduced conveying speed. Wet materials are easy to agglomerate on the conveyor belt, forming local high loads, causing the conveyor belt to run unsteadily and the conveying speed to be uneven. The humidity of the conveyed material can be obtained in real time through a humidity sensor;

[0077] The tension of the conveyor belt has a direct impact on the conveying speed. Insufficient tension may cause the conveyor belt to slip and reduce the conveying speed; excessive tension may increase the load on the roller and affect the conveying efficiency. The tension of the conveyor belt can be obtained in real time through a tension sensor.

[0078] Conveying speed refers to the speed at which the conveyor belt conveys materials, that is, the linear speed of the material moving on the conveyor belt, that is, the speed of the material along the conveying direction relative to the static position of the conveyor belt. This speed is usually measured in meters per second (m / s) or feet per minute (fpm) and can be obtained through a speed sensor.

[0079] The speed prediction module is used to train a machine learning model for predicting the transmission speed based on the comprehensive transmission influencing parameters, collect the real-time comprehensive transmission influencing parameters, and predict the transmission speed based on the trained machine learning model;

[0080] Specifically, the training method of the machine learning model that predicts the transmission speed is as follows:

[0081] Converting the collected transmission comprehensive impact parameters into a corresponding set of feature vectors;

[0082] Each group of feature vectors is used as the input of the machine learning model, the machine learning model takes the transmission speed predicted by each group of transmission comprehensive influence parameters as the output, takes the transmission speed actually corresponding to each group of transmission comprehensive influence parameters as the prediction target, and takes minimizing the loss function value of the machine learning model as the training target; training is stopped when the loss function value of the machine learning model is less than or equal to the preset target loss value.

[0083] The machine learning model may be one of SVM regression, random forest regression or neural network regression models;

[0084] The machine learning model loss function value is the mean square error;

[0085] Mean square error is one of the commonly used loss functions. By transforming the loss function formula Minimization is used as the goal to train the model so that the machine learning model better fits the data, thereby improving the performance and accuracy of the model;

[0086] In the loss function, MSE is the loss function value of the machine learning model, t is the feature vector group number; p is the number of feature vector groups; y t is the transmission speed predicted by the tth group of feature vectors, is the actual transmission speed corresponding to the tth group of feature vectors;

[0087] Other model parameters of the machine learning model, target loss value, optimization algorithm, training set test set validation set ratio, and loss function optimization are all achieved through actual engineering implementation and continuous experimental tuning.

[0088] In this embodiment, the speed of the conveyor belt can be dynamically adjusted according to the actual weight, distribution and humidity of the material to ensure that the material is transported at the optimal speed and optimize the conveying efficiency. Timely adjustment of the conveying speed can avoid accumulation or congestion of materials on the conveyor belt, reduce production line bottlenecks, and improve overall production efficiency. By considering the distribution of the material, predicting and adjusting the conveying speed, the uniform distribution of the material on the conveyor belt can be maintained to ensure the consistency and accuracy of material processing. Appropriate adjustment of the conveying speed can prevent excessive overflow or falling of the material and improve the accuracy of material processing. The conveying speed is adjusted according to the characteristics of different materials (such as weight, humidity) to improve the adaptability and processing capacity of the production line to different materials. The conveying speed is predicted and adjusted in real time, which can realize intelligent control and automated management, reduce manual intervention, and improve the automation level of the system.

[0089] Example 3

[0090] Reference Figure 6 As shown, the present invention further includes, based on Example 2:

[0091] A data acquisition module is used to acquire historical transmission data of the transmission device, the historical transmission data includes transmission device influencing parameters and a transmission parameter change set, and convert the transmission parameter change set into a transmission parameter change number, the transmission parameter change number is i=1, 2, 3....n, and n represents the total number of transmission parameter change numbers;

[0092] The transmission device influencing parameters include transmission comprehensive influencing parameters and transmission secondary influencing parameters, and the transmission secondary influencing parameters include: ambient temperature and humidity, and continuous working time of the device;

[0093] Specifically, the ambient temperature and humidity will affect the changes in the transmission parameters. Too high or too low temperature, too high humidity will affect the performance of the transmission device. The ambient temperature and humidity can be obtained through the temperature and humidity sensor;

[0094] The continuous working time of the device will affect the changes in the transmission parameters. The longer the device works continuously, the greater the possibility that the transmission device may have failures and other related parameters. The continuous working time of the device can be obtained through monitoring equipment, for example: using sensors to monitor the operating status of the transmission device in real time and record the time from the start to the stop of the device.

[0095] The transmission parameter change set is (a n , b n , c n ).

[0096] For example, when the transmission parameter change sets are numbered, i=1, 2, ... n, a, b, c correspond to the vibration, temperature and tension change rates of the transmission device, respectively, a n ,bn ,c n Indicates the vibration, temperature and tension change rates of the corresponding transmission device when the transmission parameter change number is n.

[0097] Specifically, the vibration, temperature and tension change rates corresponding to the transmission parameter change set are obtained by a vibration sensor, a temperature sensor and a tension sensor, respectively;

[0098] The tension change rate refers to the degree of change of tension per unit time. The smaller the tension change rate, the more stable the operation of the conveyor. On the contrary, a larger tension change rate indicates that there are fluctuations or unstable factors in the system. By continuously monitoring the tension change rate, the performance of the conveyor under different operating conditions can be understood.

[0099] The calculation formula of tension change rate is as follows:

[0100]

[0101] Where Zl represents the rate of change of tension, ΔT represents the change of tension, that is, the difference of tension between two time points, and Δt represents the time interval, that is, the time difference between two time points.

[0102] The parameter prediction module trains a machine learning model for predicting the transmission parameter change number at a future moment based on the transmission device influencing parameters, and then obtains the transmission parameter change set corresponding to the transmission parameter change number;

[0103] The training method of the machine learning model for predicting the number of parameter changes transmitted at future moments includes:

[0104] The transmission device influencing parameters are used as the input of the multi-feature time series prediction machine learning model, and the transmission parameter change number at future moments is used as the output of the multi-feature time series prediction machine learning model. The transmission parameter change number at future moments is used as the prediction target, and minimizing the sum of prediction accuracies of all training data is used as the training target. The multi-feature time series prediction machine learning model is trained until the sum of prediction accuracies converges and the training is stopped.

[0105] The loss function value of the machine learning model is the mean square error;

[0106] Mean square error is one of the commonly used loss functions. The model is trained with minimization as the goal, so that the machine learning model can better fit the data, thereby improving the performance and accuracy of the model.

[0107] In the loss function, MSE is the loss function value of the machine learning model, r is the feature vector group number; t is the number of feature vector groups; w rTransmit parameter change number corresponding to the future moment of the rth group of feature vectors, The parameter change number is transmitted for the future moment actually corresponding to the rth group of feature vectors.

[0108] Other model parameters of the machine learning model, target loss value, optimization algorithm, training set test set validation set ratio, and loss function optimization are all achieved through actual engineering implementation and continuous experimental tuning.

[0109] Methods for predicting the number of parameter changes transmitted at future times include:

[0110] Preset the prediction time step C, sliding step Z and sliding window length L; use the sliding window method to convert the transmission device influencing parameters into multiple training samples, one training sample corresponds to a label, and constitutes a group of training data, and multiple groups of training data constitute a training set. The training set is used as the input of the machine learning model, and the transmission parameter change number at the future moment after the prediction time step C is used as the output. The subsequent transmission parameter change number of each training set is used as the prediction target. The prediction accuracy is used as the training target to train the machine learning; generate a machine learning model that predicts the transmission parameter change number at the future moment according to the transmission device influencing parameters.

[0111] The machine learning model is one of support vector machine regression, random forest regression or neural network regression.

[0112] Specifically, a simple example of the sliding window method is as follows: assuming that you want to use the transmission device influence parameter data packets 1, 2, 3, 4, 5, 6, 7 to train a time prediction model to predict the value of the next 1 time step, you can use a sliding window of length 4 and a sliding step length of 1 to generate a predicted future training set and prediction target. For example: the training sets are 1, 2, 3, 4, 2, 3, 4, 5 and 3, 4, 5, 6, and the prediction targets are 5, 6 and 7.

[0113] The sliding window method can be used to accurately and in advance predict the transmission parameter change number at a future moment based on the existing transmission device influencing parameter data packets in the selected scheduling area, and then obtain the transmission parameter change set corresponding to the transmission parameter change number. This can enable the possible safety hazards of the transmission device to be discovered in advance when monitoring the working status of the transmission device, and provide accurate data support for subsequent early warnings, without any lag in the transmission device status monitoring.

[0114] A data analysis module generates a device stability coefficient based on a predicted set of transmission parameter changes at future moments, and generates a comprehensive evaluation result according to the device stability coefficient, wherein the comprehensive evaluation result includes a transmission device in a good state, a transmission device in a general state, and a transmission device in a poor state;

[0115] Specifically, the method for generating the device stability coefficient based on the predicted transmission parameter change set at the future moment is:

[0116]

[0117] Where Wx represents the stability coefficient of the device, Zd represents the vibration during the operation of the device, Wd represents the temperature during the operation of the device, and Zl represents the rate of change of tension during the operation of the device. represents the weight coefficient, Both are greater than 0.

[0118] It should be noted that the greater the vibration, the higher the temperature and the greater the tension change rate during the operation of the device, the smaller the corresponding device stability coefficient and the more unstable the transmission device; conversely, the smaller the vibration, the lower the temperature and the smaller the tension change rate during the operation of the device, the greater the corresponding device stability coefficient and the more stable the transmission device.

[0119] It should be noted that the formulas involved in the above-mentioned are all calculated by removing dimensions and taking numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The weight coefficients in the formulas and the various preset thresholds in the analysis process are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data; the size of the weight coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the weight coefficient depends on the amount of sample data and the corresponding processing coefficients initially set by technical personnel in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameters and the quantized values.

[0120] Generate a comprehensive evaluation result based on the device stability factor, including:

[0121] Preset device stability coefficient gradient threshold Wx 1 With Wx 2 ,Wx 1 >Wx 2 ;

[0122] If Wx≤Wx 2 , then the comprehensive evaluation result is that the device is in good condition;

[0123] If Wx 1 ≥Wx>Wx 2 , then the comprehensive evaluation result is that the device status is general;

[0124] If Wx>Wx 1 , the comprehensive evaluation result is that the device status is poor.

[0125] The staff can determine the real-time status of the conveyor according to the comprehensive evaluation results obtained in real time, and then determine whether it is necessary to shut down for inspection according to the comprehensive evaluation results, and estimate the operating status of the conveyor in advance.

[0126] In this embodiment, by predicting parameters such as future vibration, temperature, and tension change rate, potential failure risks can be identified in advance. Abnormal vibration, excessive temperature, or excessive tension change rate may indicate that the equipment is about to fail. Early warning can arrange maintenance and repairs, thereby reducing downtime and production losses caused by sudden equipment failures; evaluate the operating status of the device according to the stability coefficient, perform targeted preventive maintenance, and reduce sudden equipment failures. The stability coefficient comprehensively considers vibration, temperature, and tension change rate, and can comprehensively evaluate the stability of the conveyor device, ensure the smooth operation of the production line, and improve production efficiency; reduce downtime losses caused by equipment failures, thereby improving the continuity and efficiency of the production line.

[0127] Example 4

[0128] Reference Figure 7 As shown, the material conveying method of a power plant based on permanent magnet roller drive is applied to the above-mentioned material conveying device of a power plant based on permanent magnet roller drive, and includes the following steps:

[0129] Step 1: Collect a historical training data set of the transmission device, wherein the historical training data set includes a transmission comprehensive influencing parameter and a transmission speed;

[0130] Step 2: Train a machine learning model for predicting the transmission speed based on the comprehensive transmission influencing parameters, collect the real-time comprehensive transmission influencing parameters, and predict the transmission speed based on the trained machine learning model;

[0131] Step 3: Convey the material according to the predicted conveying speed, and use the cleaning mechanism to clean the conveyor belt surface in real time;

[0132] Step 4: Acquire historical transmission data of the transmission device, the historical transmission data includes transmission device influencing parameters and a transmission parameter change set, convert the transmission parameter change set into a transmission parameter change number, the transmission parameter change number is i=1, 2, 3....n, n represents the total number of transmission parameter change numbers;

[0133] Step 5: Based on the transmission device influencing parameters, a machine learning model is trained to predict the transmission parameter change number at a future moment, and then a transmission parameter change set corresponding to the transmission parameter change number is obtained;

[0134] Step 6: Generate a device stability coefficient based on the predicted set of transmission parameter changes at future moments, and generate a comprehensive evaluation result based on the device stability coefficient. The comprehensive evaluation result includes a transmission device in good condition, a transmission device in average condition, and a transmission device in poor condition.

[0135] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0136] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A power plant material conveying device based on permanent magnetic roller drive, characterized in that: include: Rack(100); A permanent magnetic roller (200) is rotatably mounted on both ends of the frame (100); A conveyor belt (300) is arranged on the surface of the permanent magnetic roller (200) and is used for conveying materials; A cleaning mechanism (400) is arranged at the end of the conveyor belt (300) and is used to clean the surface of the conveyor belt (300); Control systems; The cleaning mechanism (400) comprises a first cleaning component (401) and a second cleaning component (402), wherein the first cleaning component (401) and the second cleaning component (402) have the same structure and are arranged in a staggered manner relative to each other; The control system comprises: A data collection module, used to collect a historical training data set of the transmission device, wherein the historical training data set includes a transmission comprehensive influencing parameter and a transmission speed; The speed prediction module is used to train a machine learning model for predicting the transmission speed based on the comprehensive transmission influencing parameters, collect real-time comprehensive transmission influencing parameters, and predict the transmission speed based on the trained machine learning model.

2. The material conveying device for a power plant based on permanent magnetic roller drive according to claim 1 is characterized in that: The control system further comprises: A data acquisition module is used to acquire historical transmission data of the transmission device, the historical transmission data includes transmission device influencing parameters and a transmission parameter change set, and convert the transmission parameter change set into a transmission parameter change number, the transmission parameter change number is i=1, 2, 3...n, and n represents the total number of transmission parameter change numbers; The parameter prediction module trains a machine learning model for predicting the transmission parameter change number at a future moment based on the transmission device influencing parameters, and then obtains the transmission parameter change set corresponding to the transmission parameter change number; The data analysis module generates a device stability coefficient based on the predicted set of transmission parameter changes at future moments, and generates a comprehensive evaluation result based on the device stability coefficient. The comprehensive evaluation result includes a good state of the transmission device, a general state of the transmission device, and a poor state of the transmission device.

3. The material conveying device for a power plant based on permanent magnetic roller drive according to claim 1 or 2, characterized in that: The first cleaning component (401) comprises: A reciprocating cylinder (401a) fixedly mounted on the frame (100); A cleaning cylinder (401b) is evenly arranged on one side of the conveyor belt (300) and is in contact with the surface of the conveyor belt (300); The connecting frame (401c) is arranged on one side of the cleaning cylinder (401b) and is connected to the driving end of the reciprocating cylinder (401a).

4. The material conveying device for a power plant based on permanent magnetic roller drive according to claim 3 is characterized in that: The cleaning cylinder (401b) comprises: The cylinder (401b-1) is hollow inside; A fixed cavity (401b-2) is arranged on one side of the cylinder (401b-1), close to the conveyor belt (300), and communicated with the interior of the cylinder (401b-1); Exhaust holes (401b-3) are evenly distributed on one side of the fixed cavity (401b-2) and face the surface of the conveyor belt (300); A cleaning brush (401b-4) is arranged on one side of the fixed cavity (401b-2) and is in contact with the surface of the conveyor belt (300); The piston rod (401b-5) is fixedly arranged on the frame (100), and one end of the piston rod extends into the interior of the cylinder (401b-1).

5. The material conveying device for a power plant based on permanent magnetic roller drive according to claim 2, characterized in that: The machine learning model for predicting the transmission speed is trained as follows: Converting the collected transmission comprehensive impact parameters into a corresponding set of feature vectors; Each set of feature vectors is used as input of the machine learning model, the machine learning model uses the transmission speed predicted by each set of transmission comprehensive influencing parameters as output, uses the transmission speed actually corresponding to each set of transmission comprehensive influencing parameters as a prediction target, and minimizes the loss function value of the machine learning model as a training target; Stop training when the machine learning model loss function value is less than or equal to the preset target loss value; The machine learning model is SVM regression, random forest regression or neural network regression.

6. The material conveying device for a power plant based on permanent magnetic roller drive according to claim 5, characterized in that: The transmission parameter change set is (a n , b n , c n ), a, b, c correspond to the vibration, temperature and tension change rate of the conveyor respectively, a n ,b n ,c n Indicates the vibration, temperature and tension change rates of the corresponding transmission device when the transmission parameter change number is n.

7. The material conveying device for a power plant based on permanent magnetic roller drive according to claim 6, characterized in that: The method for predicting the transmission parameter change number at a future time comprises: Preset the prediction time step C, sliding step Z and sliding window length L; use the sliding window method to convert the transmission device influencing parameters into multiple training samples, one training sample corresponds to a label, and constitutes a group of training data, and multiple groups of training data constitute a training set, and use the training set as the input of the machine learning model, and predict the transmission parameter change number at the future moment after the time step C as the output, and the subsequent transmission parameter change number of each training set as the prediction target, and train the machine learning with the prediction accuracy as the training target; generate a machine learning model for predicting the transmission parameter change number at the future moment according to the transmission device influencing parameters; the machine learning model is support vector machine regression, random forest regression or neural network regression.

8. The material conveying device for a power plant based on permanent magnetic roller drive according to claim 7, characterized in that: The device stability coefficient is obtained by performing weighted calculation on the vibration, temperature and tension change rate of the transmission device at the predicted future moment.

9. The material conveying device for a power plant based on permanent magnetic roller drive according to claim 8, characterized in that: The method for generating a comprehensive evaluation result according to the device stability coefficient includes: Preset device stability coefficient gradient thresholds Wx1 and Wx2, Wx1>Wx2; If Wx≤Wx2, the comprehensive evaluation result is generated as the device status is good; If Wx1≥Wx>Wx2, the comprehensive evaluation result is generated as the device status is fair; If Wx>Wx1, a comprehensive evaluation result is generated that the device status is poor.

10. A material conveying method for a power plant based on permanent magnetic roller drive, applied to a material conveying device for a power plant based on permanent magnetic roller drive as claimed in any one of claims 1 to 9, characterized in that: The steps include: Step 1: Collect a historical training data set of the transmission device, wherein the historical training data set includes a transmission comprehensive influencing parameter and a transmission speed; Step 2: Train a machine learning model for predicting the transmission speed based on the comprehensive transmission influencing parameters, collect the real-time comprehensive transmission influencing parameters, and predict the transmission speed based on the trained machine learning model; Step 3: Convey the material according to the predicted conveying speed, and use the cleaning mechanism to clean the conveyor belt surface in real time; Step 4: Acquire historical transmission data of the transmission device, the historical transmission data includes transmission device influencing parameters and a transmission parameter change set, convert the transmission parameter change set into a transmission parameter change number, the transmission parameter change number is i=1, 2, 3...n, n represents the total number of transmission parameter change numbers; Step 5: Based on the transmission device influencing parameters, a machine learning model is trained to predict the transmission parameter change number at a future moment, and then a transmission parameter change set corresponding to the transmission parameter change number is obtained; Step 6: Generate a device stability coefficient based on the predicted set of transmission parameter changes at future moments, and generate a comprehensive evaluation result based on the device stability coefficient. The comprehensive evaluation result includes a transmission device in good condition, a transmission device in average condition, and a transmission device in poor condition.

Images