A parameter adjustment method, device, apparatus and storage medium

Abstract

The application discloses a parameter adjustment method and device, equipment and a storage medium. Through digital twinning, the decision data formed by the actual operation state, production tasks and environmental factors of the belt conveyor equipment are used to generate prediction data of cleaning force, the actual data of the cleaning force is calculated by using the physical feedback data of the actual operation of the cleaning equipment in the conveying system, the prediction data of the cleaning force is matched with the actual data, and the matching result is used as the basis for optimizing the scheduling instruction of each cleaning equipment. Through real-time sustainable iterative optimization, the parameters of the cleaning equipment are adjusted, the cleaning situation can be dynamically adjusted and controlled, the good operation condition of the conveying equipment is improved, the damage rate and failure rate of the conveying equipment and the cleaning equipment caused by unreasonable setting and long-term operation are reduced, the production efficiency is improved, and the environmental pollution is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of control, in particular to a parameter adjustment method and device, equipment and storage medium. BACKGROUND

[0002] The belt conveying device (also known as a rubber belt conveying device) is a high-efficiency continuous conveying device widely used in many industries, and is widely used in household appliances, electronics, electrical appliances, machinery, tobacco, injection molding, post and telecommunications, printing, food and other industries, and is used for assembly, detection, debugging, packaging and transportation of objects, etc. It has strong conveying capacity, long conveying distance, simple structure, easy maintenance, can be easily programmed and automatically operated, can transmit most objects or powdery and granular objects, has high speed, stable operation, low noise, and can be conveyed uphill and downhill.

[0003] In the long-term operation process, the belt conveying device often faces problems such as material sticking, dust raising and material scattering, so it is often equipped with some cleaning devices to clean the conveyor belt during operation. Common cleaning devices include scraper cleaners and intelligent water spraying cleaners, etc. However, the parameter settings of the cleaning device are mostly set according to user experience, etc., so that the cleaning effect gradually deteriorates with the operation of the device, and the cleaning effect is poor. SUMMARY

[0004] The present application provides a parameter adjustment method, device, equipment and storage medium to solve at least part of the above technical problems.

[0005] The present application provides a parameter adjustment method, device, equipment and storage medium to solve at least part of the above technical problems.

[0006] Obtaining material transportation parameters of the belt conveying system at a current control time, and first control parameters of each abutting type device and second control parameters of each pressure type device;

[0007] Based on the material transportation parameters and the pre-trained cleaning force prediction model, a predicted cleaning force generated by cleaning the conveyor belt is predicted;

[0008] Based on each first control parameter and each second control parameter, a current cleaning force of the at least one abutting type device and the at least one pressure type device for cleaning the conveyor belt at the current control time is determined;

[0009] determining third control parameters of each of the abutting devices and fourth control parameters of each of the pressure devices when cleaning the conveyor belt at a next regulation time based on the predicted cleaning force and the current cleaning force.

[0010] In a possible implementation, before the obtaining the material transportation parameters of the belt conveyor system at the current regulation time, and the first control parameters of each of the abutting devices and the second control parameters of each of the pressure devices, the method further includes:

[0011] obtaining a receiving amount of material received by a scattered material collection device in a unit time, the scattered material collection device being configured to collect material dropped by the abutting devices and the pressure devices during cleaning of the conveyor belt, and / or material scattered during transportation of the material by the belt conveyor device, the unit time being a time difference between adjacent regulation times;

[0012] if it is detected that the receiving amount is less than a preset threshold, taking the first control parameters of each of the abutting devices at the current regulation time as the third control parameters at a next regulation time, and taking the second control parameters of each of the pressure devices at the current regulation time as the fourth control parameters of the pressure devices at the next regulation time;

[0013] if it is detected that the receiving amount is not less than the preset threshold, determining that the control parameters of each of the abutting devices and each of the pressure devices need to be adjusted.

[0014] In a possible implementation, the predicting the predicted cleaning force generated by cleaning the conveyor belt based on the material transportation parameters and a pre-trained cleaning force prediction model includes:

[0015] determining that the material transportation parameters include device transportation parameters, environmental influence factor parameters, and material attribute parameters, the device transportation parameters including at least one of a load of the belt conveyor device and a belt speed, a tension, and a transportation slope of the conveyor belt, the environmental factors including at least one of a temperature, a humidity, and a wind force of a current environment, and the material attribute parameters including a water content of the material;

[0016] determining a predicted input feature vector based on the device transportation parameters, the environmental influence factor parameters, and the material attribute parameters;

[0017] inputting the predicted input feature vector into the pre-trained cleaning force prediction model to obtain a predicted cleaning force output by the cleaning force prediction model.

[0018] In a possible implementation, the determining, based on the first control parameter and the second control parameter, of a current cleaning force of the at least one abutting device and the at least one pressure device on the conveying belt at the current control moment includes:

[0019] For each abutting device, the first control parameter is used to calculate a first cleaning force of the abutting device on the conveying belt.

[0020] For each pressure device, the second control parameter is used to calculate a second cleaning force of the pressure device on the conveying belt.

[0021] The first cleaning force and / or the second cleaning force are processed by a preset order-of-magnitude normalization manner, so as to normalize the first cleaning force and the second cleaning force to the same order of magnitude.

[0022] The first cleaning force and the second cleaning force normalized by the order-of-magnitude normalization manner are fused according to a preset cleaning force fusion relationship, so as to obtain the current cleaning force of the at least one abutting device and the at least one pressure device on the conveying belt at the current control moment, wherein the cleaning force fusion relationship indicates a force exertion proportion of each abutting device and each pressure device when exerting the cleaning force on the conveying belt.

[0023] In a possible implementation, the calculating, by the first control parameter, of the first cleaning force of the abutting device on the conveying belt includes:

[0024] A first force exerted on the abutting device indicated by the first control parameter is determined.

[0025] The first cleaning force of the abutting device on the conveying belt is calculated by the first force and a length of the abutting device, the length being a length between a force-exertion position of the abutting device connected with a driving device and an abutting position of the abutting device in contact with the conveying belt.

[0026] In a possible implementation, the calculating, by the second control parameter, of the second cleaning force of the pressure device on the conveying belt includes:

[0027] A fluid density of a fluid medium sprayed by the pressure device, a radius of a fluid spraying port of the pressure device, a fluid pressure at which the pressure device sprays the fluid, and an included angle between the fluid spraying port and the conveying belt indicated by the first control parameter are determined.

[0028] A second cleaning force exerted by the pressure type device on the conveyor belt is calculated based on the fluid medium density, the radius, the fluid pressure, and the included angle.

[0029] In a possible implementation, the third control parameter of each abutting type device and the fourth control parameter of each pressure type device are determined based on the predicted cleaning force and the current cleaning force when the conveyor belt is cleaned at a next control time.

[0030] The first predicted cleaning force of each abutting type device and the second predicted cleaning force of each pressure type device are determined based on the predicted cleaning force and a preset cleaning force fusion relationship.

[0031] The first current cleaning force of each abutting type device and the second current cleaning force of each pressure type device are obtained during the process of determining the current cleaning force.

[0032] A second force applied to the abutting type device at the next control time is determined based on the first predicted cleaning force, the first current cleaning force, and a preset force compensation relationship, and the third control parameter includes the second force.

[0033] A fluid pressure at which the pressure type device sprays fluid at the next control time is determined based on the second predicted cleaning force, the second current cleaning force, and a preset fluid pressure compensation relationship, and the fourth control parameter includes the fluid pressure.

[0034] In a possible implementation, the second force applied to the abutting type device at the next control time is determined based on the first predicted cleaning force, the first current cleaning force, and a preset force compensation relationship, and includes:

[0035] A force difference value for the abutting type device is determined using the first predicted cleaning force and the first current cleaning force.

[0036] The second force applied to the abutting type device at the next control time is calculated using the preset force compensation relationship and the force difference value.

[0037] In a possible implementation, the fluid pressure at which the pressure type device sprays fluid at the next control time is determined based on the second predicted cleaning force, the second current cleaning force, and a preset fluid pressure compensation relationship, and includes:

[0038] A fluid pressure difference value at which the pressure type device sprays fluid medium is determined using the second predicted cleaning force and the second current cleaning force.

[0039] The fluid pressure at which the pressure device performs fluid ejection at the next control moment is calculated using a preset fluid pressure compensation relationship and the fluid pressure difference value.

[0040] The present disclosure also provides a parameter adjustment device, applied to a belt conveying system, the belt conveying system comprising a belt conveyor device, and at least one abutting device and at least one pressure device for cleaning a conveyor belt of the belt conveyor device, the device comprising:

[0041] a parameter acquisition module, configured to acquire a material transportation parameter of the belt conveying system at a current control moment, and a first control parameter of each abutting device and a second control parameter of each pressure device;

[0042] a cleaning force prediction module, configured to predict a predicted cleaning force generated by cleaning the conveyor belt based on the material transportation parameter and a pre-trained cleaning force prediction model;

[0043] a cleaning force determination module, configured to determine a current cleaning force of the at least one abutting device and the at least one pressure device for cleaning the conveyor belt at the current control moment based on each first control parameter and each second control parameter;

[0044] a parameter adjustment module, configured to determine a third control parameter of each abutting device and a fourth control parameter of each pressure device when cleaning the conveyor belt at a next control moment based on the predicted cleaning force and the current cleaning force.

[0045] The present disclosure also provides an electronic device, comprising a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, and the machine readable instructions are executed by the processor to perform the steps of the parameter adjustment method as described above.

[0046] The present disclosure also provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by the processor to perform the steps of the parameter adjustment method as described above.

[0047] The parameter adjustment method, device, equipment and storage medium provided by the embodiments of the present disclosure obtain the material transportation parameter of the belt conveying system at the current control moment, and the first control parameter of each abutting type device and the second control parameter of each pressure type device; based on the material transportation parameter and the pre-trained cleaning force prediction model, the predicted cleaning force generated by cleaning the conveyor belt is predicted; based on each first control parameter and each second control parameter, the current cleaning force of the at least one abutting type device and the at least one pressure type device on the conveyor belt at the current control moment is determined; based on the predicted cleaning force and the current cleaning force, the third control parameter of each abutting type device and the fourth control parameter of each pressure type device when cleaning the conveyor belt at the next control moment are determined.

[0048] In this way, by means of digital twinning, the decision data composed of the actual running state, production task and environmental factors of the belt conveying equipment generates the predicted data of the cleaning force, and the physical feedback data of the actual running of the cleaning equipment in the conveying system calculates the actual data of the cleaning force. Then the predicted data and the actual data of the cleaning force are matched, and the matching result is used as the basis for optimizing the dispatching instruction of each cleaning equipment. Through real-time sustainable iterative optimization of the parameters of the cleaning equipment, dynamic adjustment and control of the cleaning situation can be realized, the good running condition of the conveying equipment can be improved, the damage rate and failure rate of the conveying equipment and the cleaning equipment due to unreasonable setting and long-term running can be reduced, the production efficiency can be improved, and the environmental pollution can be reduced. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 It is a schematic diagram of an application scenario;

[0050] Figure 2 It is a parameter adjustment method provided by the embodiments of the present disclosure;

[0051] Figure 3 It is a mechanical analysis schematic diagram of the belt conveying system;

[0052] Figure 4 It is a schematic diagram of a parameter adjustment device provided by the embodiments of the present disclosure;

[0053] Figure 5 It is a schematic diagram of a parameter adjustment device provided by the embodiments of the present disclosure; DETAILED DESCRIPTION

[0054] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application, so that those skilled in the art can better understand the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of the present application.

[0055] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0056] According to the embodiments of the present disclosure, a method embodiment of a parameter adjustment method is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0057] Firstly, refer to Figure 1 , Figure 1 is a schematic diagram of an application scenario. As Figure 1 shown, the parameter adjustment method provided by the embodiments of the present disclosure can be applied to a belt conveying system 100, the belt conveying system 100 comprising a belt conveyor device 110, and at least one abutting device 120 and at least one pressure device 130 for cleaning a conveyor belt 111 of the belt conveyor device 110, the belt conveyor device 110 comprising the conveyor belt 111 Figure 1 only part of the conveyor belt 111) and a roller 112.

[0058] The abutting device 120 can abut against the surface of the conveyor belt 111 under the drive of a driving device such as a motor, so as to clean the material adhered and left on the conveyor belt 111. The pressure device 130 can spray fluid medium to clean the material adhered and left on the conveyor belt 111. The fluid medium sprayed by the pressure device 130 can be liquid medium (such as water) or gas medium (such as air).

[0059] In actual application, the abutting device 120 can be a scraper (as an example shown in the figure), and the pressure device 130 can be an intelligent water jet cutter. Figure 1

[0060] In addition, the belt conveyor system 100 further comprises a scattered material collecting device 140 arranged below the belt conveyor device 110, which is used to receive the material scattered from the conveyor belt 111 and the material cleaned by the abutting device 120 and the pressure device 130. It can be understood that, Figure 1 In actual application, the length and width of the scattered material collecting device 140 can be larger than those of the belt conveyor device 110, so as to completely collect the fallen material.

[0061] Please refer to Figure 2 , Figure 2 A parameter adjustment method is provided in the embodiments of the present disclosure. The parameter adjustment method provided in the embodiments of the present disclosure can be applied to the belt conveyor system 100 as shown in the figure. Figure 1

[0062] As shown in the figure, the method comprises the following steps. Figure 1

[0063] S201, acquiring the material transportation parameter of the belt conveyor system at a current control time, and the first control parameter of each abutting device and the second control parameter of each pressure device.

[0064] In this step, in the running process of the belt conveyor system, the material transportation parameter of the belt conveyor system can be acquired in real time at each control time, such as the data related to the actual running state, production task and environmental factors, and the first control parameter for controlling the abutting device and the second control parameter for controlling the pressure device can also be acquired.

[0065] ​​​The material transportation parameters include device transportation parameters, environmental influence factor parameters and material attribute parameters. The device transportation parameters include at least one of a load of the belt conveyor device and a belt speed, a tension and a transportation slope of the conveyor belt. The environmental factors include at least one of a temperature, a humidity and a wind force of a current environment. The material attribute parameters include a water content of the material. It can be understood that each of the material transportation parameters can be detected by various sensors and other devices arranged in the belt conveyor system.

[0066] It can be understood that, for the abutting device, a force is mainly applied by an electrode, a spring or a counterweight to abut on the conveyor belt. Therefore, the first control parameter can include the force applied to the abutting device, such as a torsion force applied by the electrode, a spring force or a gravity of the counterweight. The pressure device mainly provides pressure by a driving device, such as water pressure or air pressure, to realize fluid injection. Therefore, the second control parameter can include the fluid pressure provided by the pressure device for fluid injection.

[0067] During the operation of the belt conveyor system, the parameter adjustment method provided by the embodiment of the present disclosure can adjust and control the control parameters of the abutting device and the pressure device in real time. It can be understood that, the first control parameter and the second control parameter obtained in step S201 are actual control parameters used by each device at a current control time, which are obtained by adjusting and controlling at a previous control time of the current control time. When the current control time is the first control time of the operation of the belt conveyor system, i.e., when the belt conveyor system starts to operate, there is no previous control time. At this time, the corresponding preset control parameters of each device can be used for control. The preset control can be set by experience and device conditions by manual.

[0068] S202, based on the material transportation parameters and the pre-trained cleaning force prediction model, predicting a predicted cleaning force generated by cleaning the conveyor belt.

[0069] In this step, when the cleaning device needs to be dispatched, a pre-trained cleaning force prediction model can be obtained first. Then, after pre-processing the obtained material transportation parameters, the material transportation parameters are used as input data for prediction, and the cleaning force prediction model is used to predict the cleaning force.

[0070] Specifically, the prediction of the predicted cleaning force using the material transportation parameters and the pre-trained cleaning force prediction model can be to determine the equipment transportation parameters, environmental influence factor parameters and material attribute parameters contained in the material transportation parameters, the equipment transportation parameters including at least one of the load of the belt conveyor, the belt speed, the tension and the transportation slope of the belt conveyor, the environmental factors including at least one of the temperature, the humidity and the wind force of the current environment, and the material attribute parameters including the water content of the material, i.e. identifying the various parameters contained in the material transportation parameters through data identification and the like. Then, the predicted input feature vector is determined by the equipment transportation parameters, the environmental influence factor parameters and the material attribute parameters, i.e. the various parameters identified are normalized, fused and processed in a series of processes, and are arranged into the predicted input feature vector that can be used by the cleaning force prediction model. Then, the predicted input feature vector is input into the pre-trained cleaning force prediction model to obtain the predicted cleaning force output by the cleaning force prediction model.

[0071] The predicted input feature vector can be a one-dimensional feature matrix, but is not limited thereto, and can be set as a two-dimensional feature matrix, a three-dimensional feature matrix or a multi-dimensional feature matrix, etc. according to the input requirements of the cleaning force prediction model.

[0072] In the embodiments of the present disclosure, the cleaning force prediction model can be a neural network based on an online sequential extreme learning machine (OS-ELM) framework, but is not limited thereto, and other types of neural networks can also be used in other embodiments.

[0073] In actual applications, a data set that can be used can be constructed according to different working condition data and historical data of the belt conveyor system, and the data set contains a large number of feature vectors s i =(x i，real ,y i，real ). Wherein x i，real =(x 1i ,…,x ni ) is the cleaning force prediction model input feature vector, each variable in the feature vector is the measurement value at time i, and y i，real is the cleaning force prediction value at time i. Similarly, the training set and the test set required for model training can be constructed, and it can be understood that the data obtained during the use stage of the cleaning force prediction model, i.e. real-time prediction and updating iteration using new samples measured in the current stage, can also be constructed into the feature vectors in the above data set, and the difference is that part of the data does not contain y i，real .

[0074] It can be understood that all the data in the data set can be normalized first. The data set constructed is the format of the training set, test set and new sample data measured in the current stage in the cleaning force prediction model. By establishing a large number of data sets, we successfully map the physical entity of the intelligent tape conveying system to the digital space, and effectively encode the physical knowledge into the prediction and calibration model. When establishing the data set, if the expert experience or the design concept of the intelligent tape conveying system can be combined, the change range of the related physical quantity can be limited, the data under invalid working conditions can be excluded, and the representative running data can be selected, which will help to improve the generalization ability and prediction accuracy of the model.

[0075] In actual use, the training of the cleaning force prediction model can be performed using the latest samples composed of historical data. In the offline training stage, the training set is used to initialize and train the OS-ELM prediction model; in the present calibration stage, the actual data generated by the continuous iterative interaction between the virtual entity and the physical entity are used to optimize the prediction model parameters, and the prediction accuracy will be continuously self-adapted and improved in operation. And the corresponding effective prediction error boundary condition can be set, such as the ratio of the absolute value of the difference between the actual cleaning force calculated by the physical feedback data and the cleaning force prediction value obtained by the prediction model to the actual cleaning force calculated by the physical feedback data. If the effective prediction error is greater than 5%, the model training stage will directly discard the data, and in actual operation, the scheduling scheme will be recalculated to adjust the actuator in the physical entity, and whether a fault occurs will be judged in combination with the actual experience.

[0076] Immediately, the OS-ElM algorithm is divided into two stages of initialization training and optimization training. In the initialization training stage, the bias term bi of the hidden layer and the weight ωi between the input layer and the hidden layer are randomly initialized, and the initialization output weight βi, i∈[1, l] is updated by a small amount of random training samples, l is the number of hidden layer nodes, and through testing, the best number of hidden layer nodes in this application is 15. In the optimization training stage, the network output weight βi is updated by continuously iterating and calculating new samples obtained in real time. In the training, OS-ELM (online Sequential Extreme Learning Machine) updates the parameters based on the current decision end data, without retraining the historical data. Therefore, the algorithm has fast calculation speed and strong generalization ability, effectively preventing problems such as long training time and model collapse caused by increasing data sets.

[0077] In order to improve the prediction accuracy and stability of the model in the traditional OS-ELM algorithm, the Whale Optimization Algorithm (WOA) is used to optimize the bias term bi of the hidden layer and the weight ωi between the input layer and the hidden layer, and the Sigmoid function is selected as the activation function of the output layer of the model.

[0078] S203, based on each of the first control parameters and each of the second control parameters, determining a current cleaning force of the at least one abutting type device and the at least one pressure type device on the conveying belt at the current control moment.

[0079] In this step, through the detected first control parameters and second control parameters, through the force principle and mechanism of the corresponding device, etc., the current cleaning force of the conveying belt received by each cleaning device at the current control moment can be obtained. For example, the cleaning force that each device can exert can be determined respectively, and then the cleaning force of each device is unified to obtain the final current cleaning force by combining the cooperation mode and combination mode of each device.

[0080] S204, based on the predicted cleaning force and the current cleaning force, determining third control parameters of each of the abutting type devices and fourth control parameters of each of the pressure type devices at the next control moment.

[0081] It can be understood that after obtaining the predicted cleaning force and the current cleaning force, the difference between the actual cleaning condition and the ideal cleaning condition can be known through the comparison between the predicted cleaning force and the current cleaning force, and then the actual cleaning condition can be adjusted through the difference, and then the control parameters of each device that can be used at the next control moment are obtained.

[0082] In this way, the cleaning condition can be dynamically adjusted and controlled, the good running condition of the conveying device can be improved, the damage rate and failure rate of the conveying device and the cleaning device due to unreasonable setting and long-term operation can be reduced, the production efficiency can be improved, and the environmental pollution can be reduced.

[0083] In the following, some specific embodiments will be further described in combination with the above method.

[0084] Optionally, in a possible implementation, before step S201, the method further comprises:

[0085] acquire a receiving amount of material received by the loose material collecting device in a unit time, the loose material collecting device being configured to collect material dropped by the abutting device and the pressure device during cleaning of the conveyor belt, and / or material dropped during transportation of the material by the belt conveyor device, the unit time being a time difference between two adjacent control instants;

[0086] if it is detected that the receiving amount is less than a preset threshold, the first control parameter of each abutting device at a current control instant is used as a third control parameter at a next control instant, and the second control parameter of each pressure device at the current control instant is used as a fourth control parameter of the pressure device at the next control instant;

[0087] if it is detected that the receiving amount is not less than the preset threshold, it is determined that the control parameters of each abutting device and each pressure device need to be adjusted.

[0088] Here, in actual operation, the material receiving condition of the loose material collecting device can be detected in real time. By detecting the receiving amount of material received in a unit time, the material dropping condition of the belt conveyor device, the material sticking condition on the conveyor belt, and the required cleaning condition can be determined. If it is detected that the receiving amount is less than a preset threshold, it can be considered that the material dropping is less, and the amount of material that can be cleaned from the conveyor belt, such as stuck material and residual material, is also less. At this time, the demand for cleaning is relatively low, and therefore the current control parameter can be directly continued to be used, i.e., the first control parameter is used as the third control parameter at the next control instant, and the second control parameter is used as the fourth control parameter at the next control instant. Conversely, if it is detected that the receiving amount is not less than the preset threshold, it can be considered that the material dropping is more, and especially the amount of material that can be cleaned from the conveyor belt, such as stuck material and residual material, is more. In order to ensure the cleanliness of the conveyor belt, the demand for cleaning is relatively high, and the current control parameter is not sufficient to achieve better cleaning. At this time, the control parameters of each abutting device and each pressure device need to be adjusted to ensure the cleanliness and normal operation of the conveyor belt. Therefore, the process of adjusting the control parameters of each device can be started, i.e., step S2012 is started.

[0089] The preset threshold can be dynamically adjusted according to the type of the belt conveyor device and the type of the transported material. For example, when the transported material is coal, the preset threshold can be 100 grams per minute.

[0090] Optionally, in a possible implementation, step S203 includes:

[0091] For each contact-type device, the first cleaning force applied by the contact-type device to the conveyor belt is calculated using the first control parameters;

[0092] For each pressure device, the second cleaning force applied by the pressure device to the conveyor belt is calculated using the second control parameters;

[0093] By using a preset order-of-magnitude normalization method, each of the first cleaning forces and / or each of the second cleaning forces is processed to unify each of the first cleaning forces and each of the second cleaning forces to the same order of magnitude;

[0094] According to the preset cleaning force fusion relationship, the first cleaning force and the second cleaning force after being normalized to order of magnitude are fused to obtain the current cleaning force of the at least one contact device and the at least one pressure device cleaning the conveyor belt at the current control moment. The cleaning force fusion relationship indicates the force ratio of each contact device and each pressure device when applying cleaning force to the conveyor belt.

[0095] Here, as mentioned above, the contact-type device applies a cleaning force to the conveyor belt through the action of force. Therefore, using the first control parameters of each contact-type device and the preset method of the force applied by the contact-type device (which is known in advance), the first cleaning force applied by the contact-type device to the conveyor belt can be calculated. Similarly, using the working principle of the pressure-type device (which is also known in advance), the second cleaning force that it can apply can be calculated through the first control parameters.

[0096] Next, since the contact-type device and the pressure-type device are different types of devices, and their working principles, cleaning force application methods, and required steps are different, their cleaning forces are often not on the same order of magnitude. For example, the contact-type device can often apply cleaning force in the hundreds or thousands, while the pressure-type device often applies cleaning force in the single digits. Therefore, in actual data processing, a preset order of magnitude normalization method can be used to normalize the cleaning forces of the two devices to the same order of magnitude before use.

[0097] Understandably, since at least one contact-type device and at least one pressure-type device are used, the proportion of cleaning force that each device can apply varies due to differences in location, type, etc. Therefore, when calculating the resultant force, it is necessary to rely on the contribution of each device to the resultant force. For example, the proportion of cleaning force contributed by each device may be different. Therefore, when actually calculating the resultant force, a preset cleaning force fusion relationship can be used. According to the combination and contribution methods indicated in the cleaning force fusion relationship, the various cleaning forces are fused to obtain the total current cleaning force received by the conveyor belt at the current control moment.

[0098] The cleaning force fusion relationship indicates a force application ratio of each abutting device and each pressure device when applying a cleaning force to the conveyor belt. Preferably, in the embodiment of the present disclosure, the cleaning forces applied between each device can be linearly superimposed, and the cleaning force contribution ratio of each device can be one-to-one, and then the sum of the cleaning forces of each device can obtain the total current cleaning force.

[0099] Specifically, the first cleaning force applied by the abutting device to the conveyor belt is calculated through the first control parameter, including:

[0100] determining a first action force applied to the abutting device indicated by the first control parameter;

[0101] calculating the first cleaning force applied by the abutting device to the conveyor belt through the first action force and the length of the abutting device, the length being the length between the force receiving position of the abutting device connected with the driving device and the abutting position of the abutting device contacting with the conveyor belt.

[0102] It can be understood that the abutting device is used to clean the material on the conveyor belt by abutting, and the main influencing factors of the cleaning force that can be applied by the abutting device are the pre-tightening force applied by the driving device and the length of the abutting part (for example, the length of the scraper), therefore, the first cleaning force can be calculated through the first action force indicated by the first control parameter and the length of the abutting device.

[0103] Please refer to Figure 3 , Figure 3 for a schematic diagram of mechanical analysis of the belt conveyor system. As shown in Figure 3 , taking the abutting device as a scraper and the pressure device as a water jet as an example for illustration, two scrapers (for example, No. 1 scraper and No. 2 scraper) are respectively installed at points A and B, and respectively abut on points C and D on the conveyor belt, point E is the center position of the roller, and point F is the action point of the water jet on the conveyor belt.

[0104] Among them, points A and B can be considered as the center points of the rotating mechanism of No. 1 and No. 2 scrapers, which are fixed and do not change, and point E is also fixed and does not change relative to points A and B, and the positions of points C and D change with the length of the scraper.

[0105] Taking No. 1 scraper as an example, for No. 1 scraper, AE and CE are fixed lengths, respectively satisfying the following equations:

[0106] l AE =R blet +Th blet +l A，blet , l CE= R blet + Th blet ;

[0107] wherein, l AE represents the length of the AE, l CE represents the length of the CE, R blet represents the radius of the drum, Th blet represents the thickness of the conveyor belt, l A，blet represents the distance from point A to the conveyor belt, which is also a constant if point A is fixed.

[0108] In the case that the force applied to the No. 1 blade (such as the torque applied by the motor) is T, and the length of the No. 1 blade is l

[0109] f1 = T / M1;

[0110] Further, the cleaning force generated by the No. 1 blade on the conveyor belt can be:

[0111] C1 = μ1f1 = μ1T1 / M1;

[0112] Similarly, the cleaning force generated by the No. 2 blade on the conveyor belt can be:

[0113] C2 = μ2f2 = μ2T2 / M2;

[0114] wherein, μ1 and μ2 are the friction coefficients between the No. 1 blade and the No. 2 blade and the conveyor belt, respectively.

[0115] In an alternative embodiment, the calculating the first cleaning force exerted by the abutting device on the conveyor belt by the first control parameter comprises:

[0116] determining the fluid density of the fluid medium sprayed by the pressure device indicated by the first control parameter, the radius of the fluid spraying port of the pressure device, the fluid pressure at which the pressure device sprays the fluid, and the included angle between the fluid spraying port and the conveyor belt;

[0117] calculating the second cleaning force exerted by the pressure device on the conveyor belt by the fluid medium density, the radius, the fluid pressure, and the included angle.

[0118] It can be understood that the pressure type equipment is cleaned by spraying fluid medium on the conveying belt by pressure, and the influencing factors are mainly the pressure applied to the fluid, and the radius, the spray angle and the fluid medium itself of the sprayed fluid medium, so that the second cleaning force can be calculated by obtaining the parameters and the relationship between the parameters.

[0119] Also with Figure 3 The principle of water jet cleaning is to use high-pressure water flow to impact the surface of the conveying belt to strip and wash away the residual powdery material or fine dust, so as to achieve the effect of cleaning the conveying belt. The cleaning effect is related to the effective water flow and density, and the water flow is proportional to the water pressure and fluid density, and inversely proportional to the outlet diameter. According to the formula of fluid mechanics, the cleaning force C water of the water jet can be described as:

[0120] C water = aπr 2 ρpcosθ water ;

[0121] Wherein, a represents a correction parameter, which is a constant, r represents the radius of the outlet (i.e. the radius of the fluid spraying port), ρ represents the fluid density, p represents the water pressure of the water tank during work (i.e. the fluid pressure of the pressure type equipment for fluid spraying), θ water represents the angle between the water jet and the conveying belt (i.e. the angle between the fluid spraying port and the conveying belt), which is a fixed constant.

[0122] Correspondingly, after obtaining the cleaning force of each blade and the cleaning force of the water jet, according to the requirements of production task, energy consumption and environmental protection, the blade cleaner and the water jet cleaner need to work together or separately. Generally, the cleaning forces of each device are linearly superimposed by their respective proportions to obtain the total current cleaning force:

[0123] C real = a1C1+a2C2+a3C real ;

[0124] Wherein, a1, a2, a3 represent the proportion weight of the cleaning force provided by each device for fusion.

[0125] After simplifying the constant, the above formula of the current cleaning force can be expressed as:

[0126] C real = T(k1 / M1+k2 / M2)+k3p;

[0127] Wherein, the formula takes the example of the action force (such as the torque applied by the motor) of the No. 1 blade and the No. 2 blade being T, it can be understood that when T is different, the formula expands to distribute the respective T to the respective term, and k1, k2, and k3 are the constant terms of the respective devices.

[0128] It can be known from the above expression that the adjustment of the action force (such as the torque) applied to the blade and the fluid pressure (such as the water pressure of the water tank) of the fluid pressure type device for fluid injection can realize the adjustment of the cleaning force.

[0129] In a possible implementation, the step S204 comprises:

[0130] Based on the predicted cleaning force and the preset cleaning force fusion relationship, a first predicted cleaning force of each of the abutting type devices and a second predicted cleaning force of each of the pressure type devices are determined.

[0131] In the process of determining the current cleaning force, a first current cleaning force of each of the abutting type devices and a second current cleaning force of each of the pressure type devices are obtained.

[0132] Based on the first predicted cleaning force, the first current cleaning force, and the preset action force compensation relationship, a second action force applied to the abutting type devices at the next control time is determined, and the third control parameter comprises the second action force.

[0133] Based on the second predicted cleaning force, the second current cleaning force, and the preset fluid pressure compensation relationship, a fluid pressure of fluid injection by the pressure type device at the next control time is determined, and the fourth control parameter comprises the fluid pressure.

[0134] Here, after obtaining the predicted cleaning force output by the cleaning force prediction model, since the total cleaning force can be obtained by fusing the cleaning forces of the respective devices, the predicted cleaning force of the device can be obtained by means of the fusion method, that is, the first predicted cleaning force of each of the abutting type devices and the second predicted cleaning force of each of the pressure type devices can be obtained. In addition, the first current cleaning force calculated by the first control parameter of the abutting type device and the second current cleaning force calculated by the second control parameter of the pressure type device in the calculation of the current cleaning force can also be obtained.

[0135] The first predicted cleaning force and the first current cleaning force can be used to determine the difference between the actual control and the ideal control of the abutting device. In combination with a preset force compensation relationship, the actual control can be compensated, and a second force that should be applied to the abutting device at the next control time can be obtained. Similarly, the data of the pressure device can be obtained, and the fluid pressure of the pressure device at the next control time can be obtained.

[0136] It can be understood that, for the first predicted cleaning force of each abutting device and the second predicted cleaning force of each pressure device, in addition to being reversely calculated by the predicted cleaning force and a preset cleaning force fusion relationship, if the predicted cleaning force of each device can be output in the intermediate layer output of the cleaning force prediction model, the first predicted cleaning force of each abutting device and the second predicted cleaning force of each pressure device can be directly obtained from the output of the intermediate layer.

[0137] Specifically, the second force applied to the abutting device at the next control time is determined based on the first predicted cleaning force, the first current cleaning force, and a preset force compensation relationship, and includes:

[0138] The first predicted cleaning force and the first current cleaning force are used to determine the force difference value for the abutting device.

[0139] A preset force compensation relationship and the force difference value are used to calculate the second force applied to the abutting device at the next control time.

[0140] For example, the second force can be determined by the following method:

[0141] f n，t+1 = f n，t + (1-ε1)Δplate

[0142] Wherein, f n，t is the force of the nth abutting device at time t, ε1 is the force compensation coefficient included in the preset force compensation relationship, and Δplate is the force difference value between the first predicted cleaning force and the first current cleaning force, i.e. the difference between the true value and the predicted value. It can be understood that the force applied to the abutting device should be between the maximum force and the minimum force that can be provided, i.e. no matter f n，t+1 or f n，t , both should be greater than or equal to the minimum force f min , and less than or equal to the maximum force f max . The maximum force and the minimum force can be determined by the parameters of the driving device driving the abutting device, and are known constants.

[0143] Specifically, the fluid pressure of the pressure-type device for fluid injection at the next control time is determined based on the second predicted cleaning force, the second current cleaning force, and a preset fluid pressure compensation relationship, including:

[0144] The fluid pressure difference value of the pressure-type device for fluid medium injection is determined using the second predicted cleaning force and the second current cleaning force

[0145] The fluid pressure of the pressure-type device for fluid injection at the next control time is calculated using a preset fluid pressure compensation relationship and the fluid pressure difference value.

[0146] Exemplarily, the fluid pressure can be determined in the following manner:

[0147] p n，t+1 = p n，t + ε2Δwater;

[0148] wherein p n，t is the fluid pressure of the nth pressure-type device at time t, ε2 is a fluid pressure compensation coefficient indicated by the fluid pressure compensation relationship, and Δwater is the force difference value between the second predicted cleaning force and the second current cleaning force, i.e., the difference value between the actual value and the predicted value. It can be understood that the fluid pressure applied to the pressure-type device should be between the maximum pressure value that can be provided and the minimum pressure value, i.e., both p n，t+1 and p n，t should be greater than or equal to the minimum force p min and less than or equal to the maximum force p max , the maximum force and the minimum force being determined by the parameters of the driving device driving the pressure-type device and being known constants.

[0149] Based on the same inventive concept, the disclosure embodiments also provide a parameter adjustment device corresponding to the parameter adjustment method in the above. Since the principle of the device in the disclosure embodiments solves the problem similar to the above-mentioned method of the disclosure embodiments, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described here.

[0150] Please refer to Figure 4 and Figure 5 , Figure 4 is one of the schematic diagrams of a parameter adjustment device provided by the disclosure embodiments, Figure 5 is the second schematic diagram of a parameter adjustment device provided by the disclosure embodiments. The parameter adjustment device 400 provided by the disclosure embodiments can be applied to Figure 1The parameter adjustment device 400 can be an independent device or a part of any control device or computer device embedded in the belt conveying system to help the belt conveying system adjust parameters. Figure 4 As shown in the figure, the parameter adjustment device 400 includes:

[0151] A parameter acquisition module 410 is configured to acquire material transportation parameters of the belt conveying system at a current control time, and first control parameters of each abutting device and second control parameters of each pressure device.

[0152] A cleaning force prediction module 420 is configured to predict a predicted cleaning force generated by cleaning the conveyor belt based on the material transportation parameters and a pre-trained cleaning force prediction model.

[0153] A cleaning force determination module 430 is configured to determine a current cleaning force of the at least one abutting device and the at least one pressure device for cleaning the conveyor belt at the current control time based on the first control parameters and the second control parameters.

[0154] A parameter adjustment module 440 is configured to determine third control parameters of each abutting device and fourth control parameters of each pressure device for cleaning the conveyor belt at a next control time based on the predicted cleaning force and the current cleaning force.

[0155] In a possible implementation, as shown in the figure, Figure 5 The parameter adjustment device 400 further includes a control judgment module 450, which is configured to:

[0156] Acquire a receiving amount of material received by a scattered material collection device of the belt conveying system per unit time, the scattered material collection device being configured to collect material dropped by the abutting device and the pressure device during cleaning of the conveyor belt and / or material scattered during transportation of the belt conveying device, and the unit time being a time difference between adjacent control times.

[0157] If it is detected that the receiving amount is less than a preset threshold, the first control parameters of each abutting device at the current control time are used as the third control parameters at the next control time, and the second control parameters of each pressure device at the current control time are used as the fourth control parameters of the pressure device at the next control time.

[0158] If it is detected that the receiving amount is not less than the preset threshold, it is determined that the control parameters of each abutting device and each pressure device need to be adjusted.

[0159] In a possible implementation, the cleaning force prediction module 420 is specifically configured to:

[0160] determine a device transportation parameter, an environmental factor parameter and a material attribute parameter included in the material transportation parameter, the device transportation parameter including at least one of a load of the belt conveyor device and a belt speed, a tension and a transportation slope of the conveyor belt, the environmental factor including at least one of a temperature, a humidity and a wind force of a current environment, and the material attribute parameter including a water content of the material;

[0161] determine a prediction input feature vector based on the device transportation parameter, the environmental factor parameter and the material attribute parameter;

[0162] input the prediction input feature vector into a pre-trained cleaning force prediction model to obtain a predicted cleaning force output by the cleaning force prediction model.

[0163] In a possible implementation, the cleaning force determination module 430 is specifically configured to:

[0164] for each abutting device, calculate a first cleaning force exerted on the conveyor belt by the abutting device based on the first control parameter;

[0165] for each pressure device, calculate a second cleaning force exerted on the conveyor belt by the pressure device based on the second control parameter;

[0166] perform processing on each of the first cleaning forces and / or each of the second cleaning forces by using a preset order-of-magnitude normalization manner, so as to normalize each of the first cleaning forces and each of the second cleaning forces to the same order of magnitude;

[0167] fuse each of the first cleaning forces and each of the second cleaning forces normalized in the order of magnitude according to a preset cleaning force fusion relationship, to obtain a current cleaning force of the at least one abutting device and the at least one pressure device on the conveyor belt at the current control moment, wherein the cleaning force fusion relationship indicates a force exertion proportion of each of the abutting devices and each of the pressure devices when exerting the cleaning force on the conveyor belt.

[0168] In a possible implementation, the cleaning force determination module 430, in a case of being configured to calculate the first cleaning force exerted on the conveyor belt by the abutting device based on the first control parameter, is specifically configured to:

[0169] determine a first force exerted on the abutting device indicated by the first control parameter;

[0170] A first cleaning force exerted by the abutting device on the conveyor belt is calculated by the first acting force and a length of the abutting device, the length being a length between a force receiving position where the abutting device is connected to a driving device and an abutting position where the abutting device contacts the conveyor belt.

[0171] In a possible implementation, the cleaning force determination module 430 is specifically configured to, in a case where the cleaning force determination module 430 is configured to calculate a second cleaning force exerted by the pressure type device on the conveyor belt by using the second control parameter, determine a fluid density of a fluid medium sprayed by the pressure type device indicated by the first control parameter, a radius of a fluid spraying port of the pressure type device, a fluid pressure at which the pressure type device sprays the fluid, and an included angle between the fluid spraying port and the conveyor belt.

[0172] In a possible implementation, the cleaning force determination module 430 is specifically configured to, in a case where the cleaning force determination module 430 is configured to calculate a second cleaning force exerted by the pressure type device on the conveyor belt by using the second control parameter, determine a fluid density of a fluid medium sprayed by the pressure type device indicated by the first control parameter, a radius of a fluid spraying port of the pressure type device, a fluid pressure at which the pressure type device sprays the fluid, and an included angle between the fluid spraying port and the conveyor belt.

[0173] A second cleaning force exerted by the pressure type device on the conveyor belt is calculated by the fluid medium density, the radius, the fluid pressure, and the included angle.

[0174] In a possible implementation, the parameter adjustment module 440 is specifically configured to:

[0175] Based on the predicted cleaning force and a preset cleaning force fusion relationship, a first predicted cleaning force of each abutting device and a second predicted cleaning force of each pressure type device are determined.

[0176] In a possible implementation, the parameter adjustment module 440 is specifically configured to:

[0177] Based on the first predicted cleaning force, the first current cleaning force, and a preset acting force compensation relationship, a second acting force applied to the abutting device at the next control time is determined, and the third control parameter includes the second acting force.

[0178] Based on the second predicted cleaning force, the second current cleaning force, and a preset fluid pressure compensation relationship, a fluid pressure at which the pressure type device sprays the fluid at the next control time is determined, and the fourth control parameter includes the fluid pressure.

[0179] In a possible implementation, the parameter adjustment module 440 is specifically configured to, in a case where the parameter adjustment module 440 is configured to determine the second acting force applied to the abutting device at the next control time based on the first predicted cleaning force, the first current cleaning force, and the preset acting force compensation relationship, determine the second acting force applied to the abutting device at the next control time based on the first predicted cleaning force, the first current cleaning force, and the preset acting force compensation relationship.

[0180] determine, using the first predicted cleaning force and the first current cleaning force, a force difference value for the abutting device,

[0181] calculate, using a preset force compensation relationship and the force difference value, a second force applied to the abutting device at the next control moment.

[0182] In a possible implementation, the parameter adjustment module 440 is specifically configured to, in a case that the second predicted cleaning force, the second current cleaning force, and a preset fluid pressure compensation relationship are used to determine a fluid pressure at which the pressure type device sprays fluid at the next control moment, specifically:

[0183] determine, using the second predicted cleaning force and the second current cleaning force, a fluid pressure difference value at which the pressure type device sprays fluid medium

[0184] calculate, using a preset fluid pressure compensation relationship and the fluid pressure difference value, a fluid pressure at which the pressure type device sprays fluid at the next control moment.

[0185] The parameter adjustment apparatus provided by the embodiments of the present disclosure can generate predicted data of the cleaning force by means of digital twinning, with decision data composed of the actual running state, production tasks, and environmental factors of the belt type conveying device, calculate actual data of the cleaning force by means of physical feedback data of the actual running of the cleaning device in the conveying system, match the predicted data of the cleaning force with the actual data, and use the matching result as the basis for optimization of the dispatching instruction of each cleaning device. The parameters of the cleaning device can be adjusted through real-time sustainable iterative optimization, so that the cleaning situation can be dynamically adjusted and controlled, the good running state of the conveying device can be improved, the damage rate and failure rate of the conveying device and the cleaning device caused by unreasonable setting and long-term running can be reduced, the production efficiency can be improved, and the environmental pollution can be reduced.

[0186] The description of the processing procedure of each module in the apparatus and the interaction procedure between the modules can refer to the related description in the method embodiments, and will not be described in detail here.

[0187] The embodiments of the present disclosure further provide an electronic device, which comprises a processor, a memory, and a bus. The memory stores machine readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus. The machine readable instructions are executed by the processor to perform the steps of the parameter adjustment method shown in Figure 1 The steps of the parameter adjustment method shown in

[0188] The embodiment of the present disclosure further provides a computer readable storage medium, characterized in that the computer readable storage medium stores a computer program, and the computer program is run by a processor to perform the steps of the parameter adjustment method shown in the above method embodiment. Figure 1 The steps of the parameter adjustment method shown in the above method embodiment are not repeated here.

[0189] The computer program product can be implemented by hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium. In another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK) and the like.

[0190] Alternatively, the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), or the like. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method embodiments disclosed in the present application can be directly embodied as hardware processor execution, or a combination of hardware and software modules in the processor.

[0191] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other ways. Among them, the apparatus embodiments described above are only schematic, for example, the division of the units can be a logical function division, and actual implementation can have another division way, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or modules shown or discussed can be indirect coupling or communication connection through some interfaces, units or modules, which can be electrical or other forms.

[0192] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0193] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0194] When the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various program code storage media.

[0195] Finally, it should be noted that: the above-described embodiments are merely specific embodiments of the present disclosure, used to illustrate the technical solutions of the present disclosure, rather than limit them. The protection scope of the present disclosure is not limited thereto, although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any skilled person familiar with the technical field can modify or easily think of changes to the technical solutions described in the foregoing embodiments within the technical range disclosed by the present disclosure, or make equivalent replacements to some technical features; and these modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A parameter adjustment method, characterized in that, applied to a belt conveying system, the belt conveying system comprising a belt conveyor device, and at least one abutting device and at least one pressure device for cleaning a conveyor belt of the belt conveyor device, the method comprising: obtaining material transportation parameters of the belt conveying system at a current control moment, and first control parameters of each of the abutting devices and second control parameters of each of the pressure devices; based on the material transportation parameters and a pre-trained cleaning force prediction model, predicting a predicted cleaning force generated by cleaning the conveyor belt; based on each of the first control parameters and each of the second control parameters, determining a current cleaning force of the at least one abutting device and the at least one pressure device for cleaning the conveyor belt at the current control moment; based on the predicted cleaning force and the current cleaning force, determining third control parameters of each of the abutting devices and fourth control parameters of each of the pressure devices when cleaning the conveyor belt at a next control moment; wherein, based on each of the first control parameters and each of the second control parameters, determining a current cleaning force of the at least one abutting device and the at least one pressure device for cleaning the conveyor belt at the current control moment, comprises: for each abutting device, calculating a first cleaning force applied to the conveyor belt by the abutting device through the first control parameter; for each pressure device, calculating a second cleaning force applied to the conveyor belt by the pressure device through the second control parameter; processing each of the first cleaning forces and / or each of the second cleaning forces through a preset order of magnitude normalization, to unify each of the first cleaning forces and each of the second cleaning forces to the same order of magnitude; fusing each of the first cleaning forces and each of the second cleaning forces after order of magnitude normalization according to a preset cleaning force fusion relationship, to obtain a current cleaning force of the at least one abutting device and the at least one pressure device for cleaning the conveyor belt at the current control moment, wherein the cleaning force fusion relationship indicates a force application ratio of each of the abutting devices and each of the pressure devices when applying a cleaning force to the conveyor belt.

2. The method of claim 1, characterized in that, before the obtaining material transportation parameters of the belt conveying system at a current control moment, and first control parameters of each of the abutting devices and second control parameters of each of the pressure devices, the method further comprises: obtaining a receiving amount of a scattered material collecting device in a unit time, the scattered material collecting device being used to collect materials fallen by the abutting devices and the pressure devices when cleaning the conveyor belt, and / or materials scattered during the transportation of the belt conveyor device, the unit time being a time difference between adjacent two control moments; if the receiving amount is detected to be less than the preset threshold, taking the first control parameter of each abutting device at a current control moment as a third control parameter at a next control moment, and taking the second control parameter of each pressure device at the current control moment as a fourth control parameter of the pressure device at the next control moment; if the receiving amount is detected to be not less than the preset threshold, determining that the control parameters of each abutting device and each pressure device need to be adjusted.

3. The method of claim 1, wherein the predicted cleaning force generated by cleaning the conveyor belt is predicted based on the material transportation parameters and a pre-trained cleaning force prediction model, and the method further comprises: determining a device transportation parameter, an environmental influence factor parameter, and a material attribute parameter included in the material transportation parameters, the device transportation parameter including at least one of a load of the belt conveyor device and a belt speed, a tension, and a transportation slope of the conveyor belt, the environmental influence factor parameter including at least one of a temperature, a humidity, and a wind force of a current environment, and the material attribute parameter including a water content of the material; determining a prediction input feature vector based on the device transportation parameter, the environmental influence factor parameter, and the material attribute parameter; inputting the prediction input feature vector into the pre-trained cleaning force prediction model to obtain a predicted cleaning force output by the cleaning force prediction model.

4. The method of claim 3, wherein the first cleaning force exerted on the conveyor belt by the abutting device is calculated based on the first control parameter, and the method further comprises: determining a first acting force applied to the abutting device indicated by the first control parameter; calculating the first cleaning force exerted on the conveyor belt by the abutting device based on the first acting force and a length of the abutting device, the length being a length between a force receiving position of the abutting device connected to a driving device and an abutting position of the abutting device in contact with the conveyor belt.

5. The method of claim 3, wherein the second cleaning force exerted on the conveyor belt by the pressure device is calculated based on the second control parameter, and the method further comprises: determining a fluid density of a fluid medium sprayed by the pressure device, a radius of a fluid spraying port of the pressure device, a fluid pressure at which the fluid is sprayed by the pressure device, and an included angle between the fluid spraying port and the conveyor belt indicated by the first control parameter; calculating the second cleaning force exerted on the conveyor belt by the pressure device based on the fluid medium density, the radius, the fluid pressure, and the included angle.

6. The method of claim 1, wherein the third control parameter of each abutting device and the fourth control parameter of each pressure device at a next control moment when the conveyor belt is cleaned are determined based on the predicted cleaning force and the current cleaning force, and the method further comprises: ​ ​ ​ ​ determine a first predicted cleaning force of each of the abutting cleaning device and a second predicted cleaning force of each of the pressure cleaning device based on the predicted cleaning force and a preset cleaning force fusion relationship; obtain a first current cleaning force of each of the abutting cleaning device and a second current cleaning force of each of the pressure cleaning device during the current cleaning force determination process; determine a second force applied to the abutting cleaning device at the next control time based on the first predicted cleaning force, the first current cleaning force, and a preset force compensation relationship, wherein the third control parameter comprises the second force; determine a fluid pressure at which the pressure cleaning device sprays fluid at the next control time based on the second predicted cleaning force, the second current cleaning force, and a preset fluid pressure compensation relationship, wherein the fourth control parameter comprises the fluid pressure.

7. The method of claim 6, wherein determining the second force applied to the abutting cleaning device at the next control time based on the first predicted cleaning force, the first current cleaning force, and the preset force compensation relationship comprises: determining a force difference value for the abutting cleaning device using the first predicted cleaning force and the first current cleaning force; calculating the second force applied to the abutting cleaning device at the next control time using the preset force compensation relationship and the force difference value.

8. The method of claim 6, wherein determining the fluid pressure at which the pressure cleaning device sprays fluid at the next control time based on the second predicted cleaning force, the second current cleaning force, and the preset fluid pressure compensation relationship comprises: determining a fluid pressure difference value for the pressure cleaning device to spray fluid medium using the second predicted cleaning force and the second current cleaning force; calculating the fluid pressure at which the pressure cleaning device sprays fluid at the next control time using the preset fluid pressure compensation relationship and the fluid pressure difference value.

9. A parameter adjustment device, applied to a belt conveying system, the belt conveying system comprising a belt conveyor device, at least one abutting cleaning device and at least one pressure cleaning device for cleaning a conveyor belt of the belt conveyor device, the device comprising: a parameter obtaining module, configured to obtain a material transportation parameter of the belt conveying system at a current control time, and a first control parameter of each of the abutting cleaning device and a second control parameter of each of the pressure cleaning device; a cleaning force prediction module, configured to predict a predicted cleaning force generated by cleaning the conveyor belt based on the material transportation parameter and a pre-trained cleaning force prediction model; ​ The cleaning force determination module is configured to determine a current cleaning force of the at least one abutting device and the at least one pressure device on the conveyor belt at the current control moment based on the first control parameters and the second control parameters, wherein: the prediction of the predicted cleaning force generated by cleaning the conveyor belt based on the material transportation parameters and the pre-trained cleaning force prediction model comprises: determining device transportation parameters, environmental influence factor parameters and material attribute parameters contained in the material transportation parameters, the device transportation parameters comprising at least one of a load of the belt conveyor device and a belt speed, a tension and a transportation slope of the conveyor belt, the environmental influence factor parameters comprising at least one of a temperature, a humidity and a wind force of a current environment, and the material attribute parameters comprising a water content of the material; determining a prediction input feature vector through the device transportation parameters, the environmental influence factor parameters and the material attribute parameters; inputting the prediction input feature vector into the pre-trained cleaning force prediction model to obtain the predicted cleaning force output by the cleaning force prediction model; The parameter adjustment module is configured to determine third control parameters of the abutting devices and fourth control parameters of the pressure devices at a next control moment based on the predicted cleaning force and the current cleaning force.

10. An electronic device, comprising: a processor, a memory and a bus, the memory storing machine readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine readable instructions being executed by the processor to perform the steps of the parameter adjustment method according to any one of claims 1 to 8.

11. A computer readable storage medium, comprising: a computer program stored thereon, the computer program being executed by a processor to perform the steps of the parameter adjustment method according to any one of claims 1 to 8. ​

Images