Intelligent control method and device for feeding amount of crusher and readable medium

Abstract

The invention relates to the field of crusher equipment, in particular to an intelligent control method and device for the feeding amount of a crusher and a readable medium, and the method comprises the steps that S1, an initial target material level prediction model is constructed, and the initial target material level prediction model serves as a target material level prediction model of the current round to enter the next step; s2, a feeding image outside a feeding port of the crusher is obtained in real time, feeding particle size distribution is determined after the feeding image is processed, the set target load of the crusher and the feeding particle size distribution are input into the target material level prediction model of the current round, and the target material level of the current round is output; s3, the real-time feeding speed and the real-time material level are obtained, and the target feeding speed is calculated according to the real-time feeding speed, the real-time material level and the target material level of the current round so as to solve the problem of adjustment hysteresis; and S4, the feeding speed of the feeder is adjusted according to the target feeding speed, in the feeding speed adjusting process, the feeding speed or the target material level prediction model continues to be adjusted according to the real-time load of the crusher, and the steps S2-S4 are repeated.

Description

Technical Field

[0001] The present invention relates to the field of crusher equipment, and in particular to a crusher feed amount intelligent control method, device and readable medium. Background Art

[0002] In many industrial fields, crushers are essential equipment for breaking large materials into small pieces or powder. Traditional crushers usually rely on manual operation for feeding control, which may lead to problems such as uneven feeding and unstable crushing effect. If too much or too little feeding is used during the crushing process, it will lead to energy waste or reduced production capacity. At the same time, if the operation is improper, it may cause adverse effects such as overloading or damage of the crusher equipment.

[0003] With the rapid development of artificial intelligence, sensor and other technologies, the real-time monitoring and automatic adjustment of the feeding process can be achieved by real-time monitoring of the crusher feed and the operating status of the crusher host. The current monitoring and control technology is to passively adjust the feeding process by measuring the operating status of the host, which will produce obvious lag. In fact, there are situations where the operating status of the crusher host is not good, the material level is insufficient or the material level is too high, which affects the working efficiency of the crusher.

[0004] In summary, it is necessary to propose a method, device and readable medium for intelligent control of crusher feeding amount, which can predict and control the feeding situation of the crusher, solve the problem of lag in feeding process adjustment, and make the crusher always in the best working state, thereby improving production efficiency, ensuring product quality, reducing energy consumption and cost, improving production safety and complying with environmental protection regulations. Summary of the invention

[0005] The purpose of this application is to propose a crusher feed amount intelligent control method, device and readable medium to address the above-mentioned technical problems.

[0006] In a first aspect, the present invention provides a method for intelligently controlling feed amount of a crusher, comprising the following steps: S1, constructing an initial target material level prediction model, and using the initial target material level prediction model as the target material level prediction model of the current round to proceed to the next step, wherein the target material level prediction model of the current round represents the relationship between the adjustable parameters of the current round, the feed particle size distribution, the crusher target load and the target material level; S2, real-time acquisition of feed images outside the feed port of the crusher, contour extraction of particles in the feed image, obtaining contour extraction results, determining feed particle size distribution based on the contour extraction results, inputting the set crusher target load and feed particle size distribution into the target material level prediction model of the current round, and outputting the target material level of the current round; S3, obtaining the real-time feeding speed and the real-time material level, and calculating the target feeding speed according to the real-time feeding speed, the real-time material level and the target material level of the current round; S4, the target feeding speed is sent to the feeder control system, and the feeder control system adjusts the feeding speed of the feeder. During the feeding speed adjustment process of the feeder, the real-time load of the crusher is obtained to determine whether the real-time load of the crusher is within the safe load range. If so, the feeding speed of the feeder is continuously adjusted until the feeding speed of the feeder is the same as the target feeding speed. Otherwise, the adjustable parameters of the current round and the target material level prediction model of the current round are adjusted to obtain the adjustable parameters of the next round and the target material level prediction model of the next round, and the target material level prediction model of the next round is used as the target material level prediction model of the current round, and steps S2-S4 are repeated.

[0007] As a preferred method, an initial target material level prediction model is constructed, specifically including: Obtain the historical feed particle size distribution and the historical material level of the crusher under different historical loads of the crusher, and construct a function with the historical load of the crusher and the historical feed particle size distribution as independent variables and the historical material level of the crusher as the dependent variable. , where h represents the historical material level of the crusher, d represents the historical feed particle size distribution, and p represents the historical load of the crusher. Indicates adjustable parameters; The target material level prediction model is obtained by using neural network regression or least squares fitting method.

[0008] Preferably, adjusting the adjustable parameters of the current round and the target material level prediction model of the current round to obtain the adjustable parameters of the next round and the target material level prediction model of the next round specifically includes: S41, adjusting the adjustable parameters of the current round to obtain the adjusted adjustable parameters; S42, replacing the adjustable parameters of the target material level prediction model of the current round with the adjusted adjustable parameters to obtain the adjusted target material level prediction model; S43, recalculate the target material level according to the adjusted adjustable parameters, the feed particle size distribution of the current round, and the target load of the crusher of the current round to obtain the adjusted target material level. If the adjusted target material level satisfies: the ratio of the material level difference between the adjusted target material level and the target material level of the current round to the target material level of the current round is equal to the set material level adjustment ratio, execute step S44, otherwise return to step S41; S44, using the adjusted adjustable parameters as the adjustable parameters for the next round, and using the adjusted target material level prediction model as the target material level prediction model for the next round.

[0009] Preferably, the feed particle size distribution is determined based on the profile extraction result, specifically comprising: Calculate the equivalent particle size of each particle in the feed image according to the contour extraction result; The particle size range of the equivalent particle size of the particles in all feed images is divided into several particle size intervals, and the area ratio or volume ratio of the particles in all feed images in each particle size interval is calculated to obtain the feed particle size distribution.

[0010] As a preference, the target feed rate is calculated using the following formula: ; Among them, v represents the target feeding speed, v0 represents the real-time feeding speed, k represents the speed coefficient, Indicates the material level difference between the target material level of the current round and the real-time material level.

[0011] As a preference, set the feeder's feeding speed adjustment cycle, and at the beginning of each adjustment cycle, recalculate the real-time feeding speed v0 and the material level difference between the current round's target material level and the real-time material level .

[0012] In a second aspect, the present invention provides a crusher feed amount intelligent control device, comprising: A model building module is configured to build an initial target material level prediction model, and use the initial target material level prediction model as the target material level prediction model of the current round to enter the next step, wherein the target material level prediction model of the current round represents the relationship between the adjustable parameters of the current round, the feed particle size distribution, the crusher target load and the target material level; The target material level calculation module is configured to obtain a feed image outside the feed port of the crusher in real time, perform contour extraction on particles in the feed image to obtain a contour extraction result, determine the feed particle size distribution based on the contour extraction result, input the set crusher target load and feed particle size distribution into the target material level prediction model of the current round, and output the target material level of the current round; A target feeding speed calculation module is configured to obtain a real-time feeding speed and a real-time material level, and calculate a target feeding speed according to the real-time feeding speed, the real-time material level and a target material level of a current round; The adjustment module is configured to send the target feeding speed to the feeder control system, and the feeder control system adjusts the feeding speed of the feeder. During the feeding speed adjustment process of the feeder, the real-time load of the crusher is obtained to determine whether the real-time load of the crusher is within the safe load range. If so, the feeding speed of the feeder is continuously adjusted until the feeding speed of the feeder is the same as the target feeding speed. Otherwise, the adjustable parameters of the current round and the target material level prediction model of the current round are adjusted to obtain the adjustable parameters of the next round and the target material level prediction model of the next round, and the target material level prediction model of the next round is used as the target material level prediction model of the current round, and the target material level calculation module, the target feeding speed calculation module and the adjustment module are repeatedly executed.

[0013] In a third aspect, the present invention provides an electronic device comprising one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any implementation manner in the first aspect.

[0015] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method described in any implementation manner in the first aspect.

[0016] Compared with the prior art, the present invention has the following beneficial effects: (1) The present application proposes an intelligent control method for crusher feed rate, which monitors the changes in the feed particle size distribution outside the crusher feed port in real time, calculates the target material level, and adjusts the feed speed of the feeder according to the target material level before the material enters the crusher, thereby solving the problem of adjustment lag in the feeding process, ensuring that the crusher is always within the safe load range and operates efficiently under different feeding conditions, greatly reducing the situation where the crusher feeds passively and stops or runs overloaded during production, and ensuring continuous, stable and safe output of material production.

[0017] (2) The intelligent control method for crusher feed rate proposed in the present application also monitors the real-time load of the crusher during the feeding speed adjustment process, so as to respond promptly to the situation where the real-time load of the crusher exceeds the safe load range and readjust the target material level, thereby keeping the real-time load of the crusher continuously running efficiently within the safe load range, reducing the crusher from stopping feeding due to overload, thereby reducing problems such as production discontinuity, output fluctuations, and quality fluctuations. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments 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.

[0019] Figure 1 A schematic flow chart of a method for intelligently controlling feed amount of a crusher according to an embodiment of the present application; Figure 2 A schematic diagram of the structure of a crusher, a belt conveyor, an RGB camera and a 3D camera according to an embodiment of the present application; Figure 3 A schematic diagram of an intelligent control device for crusher feed amount according to an embodiment of the present application; Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application.

[0020] Figure numerals: 11, crusher; 111, main machine cavity; 12, RGB camera; 13, 3D camera; 14, belt conveyor. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all 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.

[0022] Figure 1 An intelligent control method for crusher feed amount provided by an embodiment of the present application is shown, comprising the following steps: S1, construct an initial target material level prediction model, and use the initial target material level prediction model as the target material level prediction model of the current round to enter the next step. The target material level prediction model of the current round represents the relationship between the adjustable parameters of the current round, the feed particle size distribution, the crusher target load and the target material level.

[0023] In a specific embodiment, constructing an initial target material level prediction model specifically includes: Obtain the historical feed particle size distribution and the historical material level of the crusher under different historical loads of the crusher, and construct a function with the historical load of the crusher and the historical feed particle size distribution as independent variables and the historical material level of the crusher as the dependent variable. , where h represents the historical material level of the crusher, d represents the historical feed particle size distribution, and p represents the historical load of the crusher. Indicates adjustable parameters; The target material level prediction model is obtained by using neural network regression or least squares fitting method.

[0024] Specifically, the data for constructing the initial target material level prediction model are the parameters of the crusher when it is running stably, and the specific parameters include the historical feed particle size distribution, the historical material level of the crusher, and the historical load of the crusher. When the crusher is running stably, the fluctuation of the real-time load of the crusher within a period of time is stable within the set load fluctuation range, and the historical load of the crusher obtained when constructing the initial target material level prediction model is within the set load fluctuation range. In an embodiment of the present application, the crusher target load and the crusher real-time load include but are not limited to the crusher main machine current, the crusher main machine power, and the pressure of the crusher main machine hydraulic cylinder. For example, the crusher target load is set to 90% of the rated power, and the crusher target load can also be set to other values ​​depending on the working conditions. In addition, the adjustable parameters Fine-tune the prediction result error according to the material quality or target material level. Specifically, when constructing the initial target material level prediction model, set the value of the adjustable parameter β. The value of is adjusted, and in step S4, the adjustable parameter is adjusted according to the prediction result error of the target material level. In the embodiment of the present application, the adjustable parameters of the initial target material level prediction model are The value of is set to 1 by default.

[0025] S2, real-time acquisition of feed images outside the crusher feed port, contour extraction of particles in the feed image, obtaining contour extraction results, determining feed particle size distribution based on the contour extraction results, inputting the set crusher target load and feed particle size distribution into the target material level prediction model of the current round, and outputting the target material level of the current round.

[0026] In a specific embodiment, determining the feed particle size distribution based on the profile extraction result specifically includes: Calculate the equivalent particle size of each particle in the feed image according to the contour extraction result; The particle size range of the equivalent particle size of the particles in all feed images is divided into several particle size intervals, and the area ratio or volume ratio of the particles in all feed images in each particle size interval is calculated to obtain the feed particle size distribution.

[0027] Specifically, the acquisition sensor used to collect the feed image outside the crusher feed port includes but is not limited to an RGB camera. After acquiring the feed image outside the crusher feed port, deep learning is used to extract the contours of the surface and independent particles of the feed image and calculate the feed particle size distribution. The calculation method of the feed particle size distribution is not limited to the contour equivalent ellipse short axis method. In the embodiments of the present application, reference Figure 2, an RGB camera 12 is used to collect the feed image outside the feed port of the crusher 11, and the real-time particle size distribution is obtained after processing the feed image, and the target material level of the current round is calculated using the target material level prediction model of the current round, and the target material level of the current round is within the set material level range.

[0028] S3, obtaining the real-time feeding speed and the real-time material level, and calculating the target feeding speed according to the real-time feeding speed, the real-time material level and the target material level of the current round.

[0029] In a specific embodiment, the target feeding rate is calculated using the following formula: ; Among them, v represents the target feeding speed, v0 represents the real-time feeding speed, k represents the speed coefficient, Indicates the material level difference between the target material level of the current round and the real-time material level.

[0030] In a specific embodiment, the feeder feed speed adjustment cycle is set, and at the beginning of each adjustment cycle, the real-time feed speed v0 and the material level difference between the target material level of the current round and the real-time material level are recalculated. .

[0031] Specifically, the real-time material level of the crusher is measured by a 3D camera, a lidar or a displacement sensor. When a 3D camera or a lidar is used for real-time material level measurement, the height point cloud data of the material in the main engine cavity of the crusher is obtained, and the average material level of the current material in the main engine cavity is calculated, and the average material level of the current material in the main engine cavity is used as the real-time material level; when a displacement sensor is used for real-time material level measurement, the distance between a single point or multiple points of material level and the sensor is measured, and the average material level of the current material in the main engine cavity is calculated, and the average material level of the current material in the main engine cavity is used as the real-time material level.

[0032] In the embodiment of the present application, the real-time feeding speed v0 and the material level difference between the target material level of the current round and the real-time material level are recalculated at the beginning of each adjustment cycle. , until the real-time material level is adjusted to the target material level of the current round. Figure 2 The 3D camera 13 is arranged above the main engine cavity 111 of the crusher 11. At the beginning of each adjustment cycle, the 3D camera 13 is used to collect the height point cloud data of the material in the main engine cavity 111 of the crusher 11, and the average material level of the current material in the main engine cavity 111 is calculated and used as the real-time material level.

[0033] S4, the target feeding speed is sent to the feeder control system, and the feeder control system adjusts the feeding speed of the feeder. During the feeding speed adjustment process of the feeder, the real-time load of the crusher is obtained to determine whether the real-time load of the crusher is within the safe load range. If so, the feeding speed of the feeder is continuously adjusted until the feeding speed of the feeder is the same as the target feeding speed. Otherwise, the adjustable parameters of the current round and the target material level prediction model of the current round are adjusted to obtain the adjustable parameters of the next round and the target material level prediction model of the next round, and the target material level prediction model of the next round is used as the target material level prediction model of the current round, and steps S2-S4 are repeated.

[0034] Specifically, the target feeding speed is sent to the feeder control system, and the feeder control system adjusts the feeding speed of the feeder according to the feeder model. When a belt conveyor is used for feeding, the motor frequency of the belt conveyor is adjusted to change the speed of the feed belt, thereby changing the feeding speed of the belt conveyor; when a vibrating feeder is used for feeding, the amplitude or frequency of the vibrating feeder is adjusted to change the feeding speed of the vibrating feeder. In an embodiment of the present application, when the real-time material level is lower than the target material level of the current round, the feeding speed of the feeder is increased; when the real-time material level is higher than the target material level of the current round, the feeding speed of the feeder is reduced. In an embodiment of the present application, a belt conveyor 14 is used for feeding, and the RGB camera 12 is arranged above one end of the belt conveyor 14 close to the feed port of the crusher 11, and images of the materials on the belt conveyor 14 that are about to enter the crusher 11 are captured.

[0035] Specifically, during the feeding speed adjustment process of the feeder, it is necessary to keep monitoring the real-time load of the crusher. The feeding speed of the feeder can only be adjusted within the safe load range. If the real-time load of the crusher is not within the safe load range, it is necessary to adjust the value of the adjustable parameter β and the target material level prediction model. The target material level calculated using the target material level prediction model is adjusted accordingly by adjusting the value of the adjustable parameter β and the target material level prediction model. Readjusting the feeding speed of the feeder according to the new target material level of the current round and entering the step of verifying the real-time load of the crusher can ensure that the crusher always works within the safe load range, thereby reducing the situation where the crusher stops feeding due to overload, and reducing problems such as discontinuous production, output fluctuations, and quality fluctuations.

[0036] In an embodiment of the present application, the real-time material level reaches the target material level by adjusting the feeding speed of the feeder, and before the feed particle size distribution changes, the fluctuation of the real-time material level is kept stable within the set material level fluctuation range until the feed particle size distribution changes, and a new target material level needs to be re-determined.

[0037] In a specific embodiment, adjusting the adjustable parameters of the current round and the target material level prediction model of the current round to obtain the adjustable parameters of the next round and the target material level prediction model of the next round specifically includes: S41, adjusting the adjustable parameters of the current round to obtain the adjusted adjustable parameters; S42, replacing the adjustable parameters of the target material level prediction model of the current round with the adjusted adjustable parameters to obtain the adjusted target material level prediction model; S43, recalculate the target material level according to the adjusted adjustable parameters, the feed particle size distribution of the current round, and the target load of the crusher of the current round to obtain the adjusted target material level. If the adjusted target material level satisfies: the ratio of the material level difference between the adjusted target material level and the target material level of the current round to the target material level of the current round is equal to the set material level adjustment ratio, execute step S44, otherwise return to step S41; S44, using the adjusted adjustable parameters as the adjustable parameters for the next round, and using the adjusted target material level prediction model as the target material level prediction model for the next round.

[0038] Specific, adjustable parameters Fine-tuning can be performed based on the predicted result error of the material material or the target material level. The predicted result error of the target material level means that when the feeding speed of the feeder is adjusted according to the target material level of the current round, the real-time load of the crusher is not within the safe load range. Therefore, adjusting the feeding speed of the feeder according to the target material level of the current round cannot make the crusher reach the optimal operating state. This means that there is an error between the target material level of the current round and the ideal target material level, and the adjustable parameters of the current round need to be adjusted. The target material level prediction model of the current round is adjusted so that the target material level calculated according to step S2 is close to the ideal target material level. When the feeding speed of the feeder is adjusted so that the real-time material level reaches the ideal target material level and the crusher maintains stable operation, the crusher can always be in the best working state, improve work efficiency, and solve the problems of energy waste caused by too low material level, reduced productivity and quality caused by too high material level. Furthermore, the operating state of the crusher during crushing will be different due to different material materials, which will also lead to errors in the prediction results of the target material level. In the process of adjusting the adjustable parameters and the target material level prediction model, the adjusted target material level is recalculated according to the adjusted adjustable parameters and the adjusted target material level prediction model. The adjusted target material level must meet the following requirements: the ratio of the material level difference between the adjusted target material level and the target material level of the current round to the target material level of the current round is equal to the set material level adjustment ratio. For example, if the material level adjustment ratio is set to 10%, the adjusted target material level calculated by the adjusted target material level prediction model is reduced to 90% of the target material level of the current round or increased to 110% of the target material level of the current round. By adjusting the adjustable parameters and the target material level prediction model, the target material level is adjusted according to the material level adjustment ratio, and the adjusted adjustable parameters and target material level prediction model are used as the adjustable parameters of the next round and the target material level prediction model of the next round, so as to update the target material level prediction model.

[0039] Furthermore, when the real-time load of the crusher is less than the minimum value of the safe load range, the adjustable parameters are adjusted. and a target material level prediction model, so that the adjusted target material level calculated by the adjusted target material level prediction model increases the material level height corresponding to the material level adjustment ratio compared to the target material level of the current round, and the adjusted target material level is within the set material level range. In particular, when the target material level is adjusted to the maximum value of the set material level range, the target material level is maintained at the maximum value of the set material level range, and the target material level is not adjusted; when the real-time load of the crusher is greater than the maximum value of the safe load range, the adjustable parameters are adjusted. And the target material level prediction model, so that the adjusted target material level calculated by the adjusted target material level prediction model is lower than the target material level of the current round by the material level height corresponding to the material level adjustment ratio, and the adjusted target material level is within the set material level range.

[0040] The above steps S1-S4 do not necessarily represent the order between the steps, but are represented by step symbols, and the order between the steps can be adjusted.

[0041] Further references Figure 3 As an implementation of the methods shown in the above figures, the present application provides an embodiment of an intelligent control device for crusher feed amount, and the device embodiment is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0042] The embodiment of the present application provides a crusher feed amount intelligent control device, comprising: Model building module 1 is configured to build an initial target material level prediction model, and use the initial target material level prediction model as the target material level prediction model of the current round to enter the next step, and the target material level prediction model of the current round represents the relationship between the adjustable parameters of the current round, the feed particle size distribution, the crusher target load and the target material level; The target material level calculation module 2 is configured to obtain a feed image outside the feed port of the crusher in real time, perform contour extraction on particles in the feed image, obtain a contour extraction result, determine the feed particle size distribution based on the contour extraction result, input the set crusher target load and feed particle size distribution into the target material level prediction model of the current round, and output the target material level of the current round; The target feeding speed calculation module 3 is configured to obtain the real-time feeding speed and the real-time material level, and calculate the target feeding speed according to the real-time feeding speed, the real-time material level and the target material level of the current round; The adjustment module 4 is configured to send the target feeding speed to the feeder control system, and the feeder control system adjusts the feeding speed of the feeder. During the feeding speed adjustment process of the feeder, the real-time load of the crusher is obtained to determine whether the real-time load of the crusher is within the safe load range. If so, the feeding speed of the feeder is continuously adjusted until the feeding speed of the feeder is the same as the target feeding speed. Otherwise, the adjustable parameters of the current round and the target material level prediction model of the current round are adjusted to obtain the adjustable parameters of the next round and the target material level prediction model of the next round, and the target material level prediction model of the next round is used as the target material level prediction model of the current round, and the target material level calculation module 2, the target feeding speed calculation module 3 and the adjustment module 4 are repeatedly executed.

[0043] Figure 4 Schematic diagram of the hardware structure of the electronic device provided by the embodiment of the present invention. Figure 4 As shown, the electronic device of this embodiment includes: a processor 401 and a memory 402; wherein the memory 402 is used to store computer-executable instructions; the processor 401 is used to execute the computer-executable instructions stored in the memory to implement the various steps performed by the electronic device in the above embodiment. For details, please refer to the relevant description in the above method embodiment.

[0044] Optionally, the memory 402 may be independent or integrated with the processor 401 .

[0045] When the memory 402 is independently provided, the electronic device further includes a bus 403 for connecting the memory 402 and the processor 401 .

[0046] The embodiment of the present invention further provides a computer storage medium, in which computer execution instructions are stored. When the processor 401 executes the computer execution instructions, the above method is implemented.

[0047] The embodiment of the present invention further provides a computer program product, including a computer program. When the computer program is executed by the processor 401, the above method is implemented.

[0048] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0049] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

[0050] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each module may exist physically separately, or two or more modules may be integrated into one unit. The above-mentioned module-composed unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0051] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor 401 to perform some steps of the methods of various embodiments of the present application.

[0052] It should be understood that the processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or the processor 401 may be any conventional processor 401, etc. The steps of the method disclosed in the invention may be directly embodied in the execution of the hardware processor 401, or may be executed by a combination of hardware and software modules in the processor 401.

[0053] The memory 402 may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk, or an optical disk.

[0054] The bus 403 may be an Industry Standard Architecture (ISA), a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus 403 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus 403 in the drawings of the present application is not limited to only one bus 403 or one type of bus 403.

[0055] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0056] An exemplary storage medium is coupled to the processor 401, so that the processor 401 can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor 401. The processor 401 and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor 401 and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0057] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A crusher feed rate intelligent control method, characterized in that: The following steps are involved: S1, constructing an initial target material level prediction model, and using the initial target material level prediction model as the target material level prediction model of the current round to proceed to the next step, wherein the target material level prediction model of the current round represents the relationship between the adjustable parameters of the current round, the feed particle size distribution, the crusher target load and the target material level; S2, acquiring a feed image outside the feed port of the crusher in real time, performing contour extraction on particles in the feed image to obtain a contour extraction result, determining a feed particle size distribution based on the contour extraction result, inputting a set crusher target load and the feed particle size distribution into a target material level prediction model for the current round, and outputting a target material level for the current round; S3, obtaining a real-time feeding speed and a real-time material level, and calculating a target feeding speed according to the real-time feeding speed, the real-time material level and the target material level of the current round; S4, sending the target feeding speed to the feeder control system, which adjusts the feeding speed of the feeder. During the feeding speed adjustment process of the feeder, the real-time load of the crusher is obtained to determine whether the real-time load of the crusher is within the safe load range. If so, the feeding speed of the feeder is continuously adjusted until the feeding speed of the feeder is the same as the target feeding speed. Otherwise, the adjustable parameters of the current round and the target material level prediction model of the current round are adjusted to obtain the adjustable parameters of the next round and the target material level prediction model of the next round. The target material level prediction model of the next round is used as the target material level prediction model of the current round, and steps S2-S4 are repeated.

2. The intelligent control method for crusher feed amount according to claim 1, characterized in that: The construction of the initial target material level prediction model specifically includes: Obtain the historical feed particle size distribution of the crusher under different historical loads of the crusher and the historical material level of the crusher, and construct a function using the historical load of the crusher and the historical feed particle size distribution as independent variables and the historical material level of the crusher as a dependent variable. , where h represents the historical material level of the crusher, d represents the historical feed particle size distribution, and p represents the historical load of the crusher. Indicates adjustable parameters; The target material level prediction model is obtained by using neural network regression or least squares fitting method.

3. The intelligent control method for crusher feed amount according to claim 2, characterized in that: The adjusting the adjustable parameters of the current round and the target material level prediction model of the current round to obtain the adjustable parameters of the next round and the target material level prediction model of the next round specifically includes: S41, adjusting the adjustable parameters of the current round to obtain adjusted adjustable parameters; S42, replacing the adjustable parameters of the target material level prediction model of the current round with the adjusted adjustable parameters to obtain the adjusted target material level prediction model; S43, recalculating the target material level according to the adjusted adjustable parameters, the feed particle size distribution of the current round, and the target load of the crusher of the current round to obtain the adjusted target material level. If the adjusted target material level satisfies: the ratio of the material level difference between the adjusted target material level and the target material level of the current round to the target material level of the current round is equal to the set material level adjustment ratio, then executing step S44, otherwise returning to step S41; S44, using the adjusted adjustable parameters as the adjustable parameters for the next round, and using the adjusted target material level prediction model as the target material level prediction model for the next round.

4. The intelligent control method for crusher feed amount according to claim 1, characterized in that: Determining the feed particle size distribution based on the profile extraction result specifically includes: Calculating the equivalent particle size of each particle in the feed image according to the contour extraction result; The particle size range of the equivalent particle size of all particles in the feed image is divided into several particle size intervals, and the area ratio or volume ratio of all particles in the feed image in each particle size interval is calculated to obtain the feed particle size distribution.

5. The intelligent control method for crusher feeding amount according to claim 1 is characterized in that: The target feed rate is calculated using the following formula: ； Among them, v represents the target feeding speed, v0 represents the real-time feeding speed, k represents the speed coefficient, Indicates the material level difference between the target material level of the current round and the real-time material level.

6. The intelligent control method for crusher feeding amount according to claim 5 is characterized in that: Set the feed speed adjustment cycle of the feeder. At the beginning of each adjustment cycle, recalculate the real-time feed speed v0 and the material level difference between the target material level of the current round and the real-time material level. .

7. An intelligent control device for crusher feed rate, characterized in that: include: A model building module is configured to build an initial target material level prediction model, and use the initial target material level prediction model as the target material level prediction model of the current round to enter the next step, wherein the target material level prediction model of the current round represents the relationship between the adjustable parameters of the current round, the feed particle size distribution, the crusher target load and the target material level; a target material level calculation module, configured to obtain a feed image outside a feed port of a crusher in real time, perform contour extraction on particles in the feed image to obtain a contour extraction result, determine a feed particle size distribution based on the contour extraction result, input a set crusher target load and the feed particle size distribution into a target material level prediction model for the current round, and output a target material level for the current round; a target feeding speed calculation module, configured to obtain a real-time feeding speed and a real-time material level, and calculate a target feeding speed according to the real-time feeding speed, the real-time material level and the target material level of the current round; The adjustment module is configured to send the target feeding speed to the feeder control system, and the feeder control system adjusts the feeding speed of the feeder. During the feeding speed adjustment process of the feeder, the real-time load of the crusher is obtained to determine whether the real-time load of the crusher is within the safe load range. If so, the feeding speed of the feeder is continuously adjusted until the feeding speed of the feeder is the same as the target feeding speed. Otherwise, the adjustable parameters of the current round and the target material level prediction model of the current round are adjusted to obtain the adjustable parameters of the next round and the target material level prediction model of the next round, and the target material level prediction model of the next round is used as the target material level prediction model of the current round, and the target material level calculation module, the target feeding speed calculation module and the adjustment module are repeatedly executed.

8. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images