SCM sand making process optimization system based on Internet of Things

Abstract

The invention relates to the technical field of sand making process optimization, in particular to an SCM sand making process optimization system based on the Internet of Things, and provides the following scheme that the system comprises a self-adaptive crushing module, an intelligent screening module, a grinding control module, an intelligent conveying module and a feedback optimization module. And the self-adaptive crushing module adjusts working parameters of crushing equipment in real time according to material characteristics through material identification and equipment adjustment logic. The intelligent screening module achieves material granularity monitoring and blockage prediction and adjustment in the screening process through granularity monitoring and material blockage prediction logic. And the grinding control module dynamically adjusts the pressure and the rotating speed of the grinding equipment by monitoring the dust change in real time. The intelligent conveying module achieves optimization of the speed and the inclination angle of the conveying belt through material flow monitoring and conveying parameter adjustment. And the feedback optimization module optimizes and adjusts parameters of each module of the system according to the finished product quality data. Through intelligent regulation and control, the efficiency of the sand making process and the product quality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sand making process optimization, and in particular to a SCM sand making process optimization system based on the Internet of Things. Background Art

[0002] With the acceleration of industrialization, sand making technology has played an increasingly important role in construction, infrastructure and industrial production. Traditional sand making technology has certain limitations in production efficiency, finished product quality and energy consumption control, and it is difficult to meet the needs of modern industrial production for high efficiency, stability and fine control. Especially in the face of diversified raw materials and complex process requirements, the manual adjustment and experience management methods of traditional equipment are often difficult to achieve precise control, resulting in fluctuations and instability in the production process. The development of Internet of Things (IoT) technology has brought new opportunities for the intelligence and automation of sand making technology. By applying IoT technology to sand making technology, real-time monitoring, intelligent analysis and dynamic adjustment of key parameters in the production process can be achieved, thereby significantly improving production efficiency, optimizing energy consumption, improving finished product quality and reducing the need for manual intervention.

[0003] For example, the Chinese patent with publication number CN116786758A discloses a sand particle size optimization process for casting compressor cylinder seats, which includes the following steps: setting the initial target value of the sand particle size (AFS), feeding 100 / 200 mesh silica sand and 70 / 140 mesh silica sand alternately into the new sand hopper according to the requirements of the initial target value of the sand particle size (AFS), tracking and counting the sand sticking situation of the silencer cavity of the cylinder seat during the same period, determining the optimal sand particle size (AFS) value, formulating a new standard of silica sand as 140 / 70 mesh silica sand, and providing it to the silica sand supplier. The sand particle size is optimized through this application, which significantly improves the problem of sand sticking in the silencer cavity of the cylinder seat, and the new standard silica sand model is formulated according to the optimized sand particle size and provided to the silica sand supplier, so that the silica sand supplier can make and directly provide silica sand that meets the requirements, eliminating the silica sand mixing process, reducing the amount of coal powder added in the sand molding process that has the effect of preventing sand sticking, and reducing the cost of casting materials.

[0004] The above patents all have the problems raised by this background technology: when faced with diverse raw materials and complex process requirements, the manual adjustment and experience management methods of traditional equipment are often difficult to achieve precise control, resulting in fluctuations and instability in the production process. To solve the above problems, this application designs an SCM sand making process optimization system based on the Internet of Things. Summary of the invention

[0005] The technical problem to be solved by the present invention is to address the deficiencies of the prior art and provide an SCM sand making process optimization system based on the Internet of Things. The system includes an adaptive crushing module, an intelligent screening module, a grinding control module, an intelligent conveying module and a feedback optimization module. The adaptive crushing module adjusts the working parameters of the crushing equipment in real time according to the material characteristics through material identification and equipment adjustment logic. The intelligent screening module realizes material particle size monitoring and blockage prediction and adjustment during screening through particle size monitoring and material blockage prediction logic. The grinding control module dynamically adjusts the pressure and speed of the grinding equipment by real-time monitoring of dust changes. The intelligent conveying module optimizes the conveyor belt speed and inclination by material flow monitoring and conveying parameter adjustment. The feedback optimization module optimizes and adjusts the parameters of each module of the system according to the finished product quality data. The system improves the efficiency of the sand making process and product quality through intelligent regulation.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The SCM sand making process optimization system based on the Internet of Things includes:

[0008] Adaptive crushing module, intelligent screening module, grinding control module, intelligent conveying module and feedback optimization module;

[0009] The adaptive crushing module is configured with a crushing optimization strategy, which is used to adjust the working parameters of the crushing equipment in real time according to the material characteristics;

[0010] The intelligent screening module is equipped with a particle size monitoring strategy, which is used to monitor the particle size of the material and predict the material clogging trend during the screening process;

[0011] The grinding control module is used to adjust the pressure and speed of the grinding equipment according to the change of the particle size of the material during the grinding process;

[0012] The intelligent conveying module is used to monitor the material flow and conveying status and adjust the conveyor belt speed and inclination;

[0013] The feedback optimization module is used to optimize the working parameters of the system modules according to the quality of the finished product.

[0014] The adaptive crushing module comprises:

[0015] A material identification unit, used to collect physical property data of the material and identify the type of the material according to the physical property data;

[0016] A crushing equipment adjustment unit, used to adjust the working parameters of the crushing equipment according to the material type output by the material identification unit;

[0017] The crushing optimization strategy includes material identification logic and equipment adjustment logic. The material identification logic is used to calculate the material feature vector according to the physical property data, train the material feature vector by building a feature classification network, and identify the type of material. The equipment adjustment logic is used to adjust the initial crushing parameters of the crushing equipment.

[0018] The material identification logic is configured in the material identification unit, and the equipment adjustment logic is configured in the crushing equipment adjustment unit.

[0019] The device adjustment logic includes:

[0020] Querying a preset parameter mapping table according to the material type to determine initial crushing parameters, wherein the initial crushing parameters include crushing force, rotation speed and feed speed;

[0021] Calculating the fitness of the initial crushing parameters according to the crushing equipment data, iteratively optimizing the fitness according to the genetic algorithm, and calculating the optimal fitness of the initial crushing parameters;

[0022] Dynamically adjusting the initial crushing parameters according to the material characteristic vector, the optimal fitness and the initial crushing parameters, and calculating the optimal crushing parameters;

[0023] The crushing equipment operation data fed back by the monitoring sensor is compared with the optimal crushing parameters. If the deviation is greater than the operation threshold, the crushing parameters of the crushing equipment are adjusted for the second time.

[0024] The calculation formula of the optimal crushing parameters is:

[0025]

[0026] Among them, B c represents the optimal crushing parameter, F a Indicates the adjusted crushing force, N a Indicates the adjusted speed, V a Indicates the adjusted feed rate, f b represents the optimal fitness of the initial crushing parameters, F represents the initial crushing force, N represents the initial rotation speed, V represents the initial feed rate, ΔH represents the deviation value of the material hardness coefficient from the standard hardness coefficient, H co Indicates the material hardness coefficient, k H Indicates the adjustment coefficient of the material hardness coefficient characteristics, ΔW indicates the deviation of the material humidity ratio from the standard humidity ratio, k W The adjustment factor representing the material moisture ratio, W ra Indicates the material moisture ratio, k D Indicates the adjustment coefficient between the material particle size distribution and the standard particle size distribution, D 50Represents the median value of the material particle size distribution, σ D represents the distribution deviation of the material particle size distribution, D represents the material particle size distribution, k ρ represents the adjustment coefficient between material density and standard density, ρ represents material density, k C It represents the adjustment coefficient between the mineral composition of the material and the standard mineral composition, ΔC represents the deviation value between the mineral composition of the material and the standard mineral composition, and C represents the mineral composition of the material.

[0027] The intelligent screening module comprises:

[0028] The particle size monitoring unit is used to monitor the particle size distribution of each layer of materials during the screening process in real time;

[0029] The screening prediction unit is used to predict the particle size monitoring data, determine whether there is a blockage, and adjust the vibration frequency, amplitude and screen angle of the screening equipment according to the blockage situation;

[0030] Screen cleaning unit to remove deposits from the screening process;

[0031] The particle size monitoring strategy includes particle size distribution monitoring logic and material blockage prediction logic;

[0032] The particle size distribution monitoring logic is configured in the particle size monitoring unit, and the material blockage prediction logic is configured in the screening prediction unit.

[0033] The particle size distribution monitoring logic includes:

[0034] Collecting flow images during material screening by an optical camera, and preprocessing the flow images, wherein the preprocessing includes linear enhancement and noise removal;

[0035] Traverse each pixel in the preprocessed flow image, calculate the sum of the grayscale weighted differences between the pixel neighborhood and the pixel, compare the sum of the grayscale weighted differences with the binarization threshold, and if it is less than the binarization threshold, set the pixel to zero to obtain a particle binarization image;

[0036] The peak values ​​of the binary particle image are counted by Hough transform, the horizontal coordinates of the parallel lines are determined according to the peak values, the particle flow area is obtained according to the upper and lower boundary coordinates of the binary particle image and the horizontal coordinates of the parallel lines, all white pixels in the particle flow area are projected, and the flow particle image is extracted;

[0037] Marking the pixel edge point coordinates of each flow particle image, extracting the particle area feature, and calculating the particle flow feature according to the variance of the particle area feature;

[0038] Divide each flow particle image into sub-regions in an equidistant manner according to the horizontal and vertical directions, extract the area features of the sub-regions, and calculate the particle stability features according to the standard deviation of the area features of the sub-regions;

[0039] The particle flow characteristics and particle stability characteristics are fused through a 1×1 convolution kernel to calculate the particle uniformity characteristics;

[0040] The particle size distribution curve of each layer of the sieve is calculated according to the uniform characteristics of the particles.

[0041] The material blockage prediction logic includes:

[0042] Vibration sensors, acceleration sensors and acoustic wave sensors distributed on each layer of the screening equipment can collect the vibration frequency, amplitude, material flow rate and acoustic wave signal intensity of each layer of materials in the screening process in real time;

[0043] Preprocess the collected vibration frequency, amplitude, material flow rate, acoustic wave signal, image data and laser reflection intensity data, including filtering, denoising and standardization. Use time series analysis methods to time-calibrate the processed data and establish a multi-dimensional time series data set.

[0044] Extract key characteristic parameters from the preprocessed data, including the vibration frequency change rate, amplitude change rate, material flow rate fluctuation amplitude, acoustic signal intensity fluctuation, area ratio of material accumulation in the image, and laser reflection intensity change;

[0045] A material blockage prediction model is constructed based on historical screening data. The current key characteristic parameters are input into the trained prediction model. The material blockage probability of each layer of the screen is calculated in real time. According to the blockage probability output by the model, it is determined whether there is a material blockage trend and the corresponding prediction results are output.

[0046] The grinding control module comprises:

[0047] Dust change monitoring unit, used to monitor the dust change distribution of materials in the grinding process in real time through a high-precision laser particle size analyzer;

[0048] The equipment control unit is used to dynamically adjust the working pressure and speed of the grinding equipment based on the real-time data provided by the dust conversion monitoring unit, including:

[0049] Use PID control algorithm to adjust the pressure and speed of the grinding equipment through closed-loop feedback;

[0050] When abnormal dust fluctuations are detected, the grinding roller pressure or grinding disc speed is automatically adjusted.

[0051] The intelligent transport module comprises:

[0052] Material flow monitoring unit, used to monitor the material flow and conveying status in real time through the material flow sensor and weight sensor installed on the conveyor belt;

[0053] The conveying parameter dynamic adjustment unit is used to automatically adjust the speed and inclination of the conveyor belt according to the data provided by the material flow monitoring unit;

[0054] When the material flow is detected to be too large or too small, the conveyor belt speed is automatically adjusted to avoid material accumulation or poor conveying.

[0055] When the conveying inclination angle is not suitable for the current material characteristics, the conveyor belt inclination angle is automatically adjusted according to the physical characteristics of the material to ensure the conveying efficiency;

[0056] The conveying path optimization unit is used to intelligently select the optimal conveying path based on real-time material flow data to avoid congestion and unnecessary energy consumption.

[0057] The feedback optimization module comprises:

[0058] Finished product quality monitoring unit, used to monitor the particle size, humidity and density of finished product materials in real time according to the quality inspection equipment;

[0059] The parameter optimization logic unit is used to analyze whether the working parameters of each module in the current production process meet expectations based on the data fed back by the finished product quality monitoring unit. When the quality of the finished product deviates, the system optimizes and adjusts the working parameters of each module.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] Through intelligent monitoring and dynamic adjustment of each module, the system of the present invention can optimize each link of the sand making process in real time, reduce human intervention, and significantly improve overall production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0063] Figure 1 This is a module diagram of an SCM sand making process optimization system based on the Internet of Things according to an embodiment of the present invention;

[0064] Figure 2 This is a characteristic classification network structure diagram of an embodiment of the present invention;

[0065] Figure 3 This is a flow chart of logic steps for adjusting the device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0067] Example

[0068] See also Figure 1 , an embodiment provided by the present invention: an SCM sand making process optimization system based on the Internet of Things, the system comprising:

[0069] Adaptive crushing module, intelligent screening module, grinding control module, intelligent conveying module and feedback optimization module;

[0070] The adaptive crushing module is configured with a crushing optimization strategy, which is used to adjust the working parameters of the crushing equipment in real time according to the material characteristics;

[0071] The intelligent screening module is equipped with a particle size monitoring strategy, which is used to monitor the particle size of the material and predict the material distribution trend during the screening process;

[0072] The grinding control module is used to adjust the pressure and speed of the grinding equipment according to the change of the particle size of the material during the grinding process;

[0073] The intelligent conveying module is used to monitor the material flow and conveying status and adjust the conveyor belt speed and inclination;

[0074] The feedback optimization module is used to optimize the working parameters of the system modules according to the quality of the finished product.

[0075] The adaptive crushing module comprises:

[0076] A material identification unit, used to collect physical property data of the material and identify the type of the material according to the physical property data;

[0077] A crushing equipment adjustment unit, used to adjust the working parameters of the crushing equipment according to the material type output by the material identification unit;

[0078] The crushing optimization strategy includes material identification logic and equipment adjustment logic, wherein the material identification logic is configured in the material identification unit, and the equipment adjustment logic is configured in the crushing equipment adjustment unit;

[0079] The adaptive crushing module also includes a fault detection and early warning mechanism. When abnormal data (such as high temperature or excessive vibration) is detected, an early warning is automatically triggered to prompt the operator or automatically take protective measures, such as reducing the equipment speed or suspending the crushing process.

[0080] Material identification logic, including:

[0081] Through the IoT sensor network, the raw materials entering the crushing equipment are collected in real time to obtain physical property data, including hardness, moisture, particle size distribution, density and mineral composition;

[0082] Standardize the collected physical property data and use the Kalman filter to perform real-time data smoothing to eliminate noise caused by differences in sensor accuracy or environmental conditions;

[0083] Extract key characteristic parameters from the filtered physical property data, calculate the material hardness coefficient according to the hardness, calculate the material moisture ratio according to the moisture, and calculate the material physical coefficient according to the particle size distribution, density and mineral components;

[0084] Encoding the key characteristic parameters and calculating the material characteristic vector;

[0085] See also Figure 2 , a structural diagram of a feature classification network according to an embodiment of the present invention, constructing a feature classification network, taking the material feature vector as an input parameter of the feature classification network, training the input parameter through the material feature vector, and outputting a material type;

[0086] The feature classification network includes an input layer, a hidden layer and an output layer. The input layer is used to input a material feature vector, perform logarithmic operations and size reconstruction on the material feature vector, and obtain input parameters. The hidden layer is used to train the input parameters and calculate material category parameters. The output layer is used to output classification results according to the material category parameters.

[0087] The input layer includes logarithmic operation, size reconstruction and convolution;

[0088] The hidden layer includes a processing module A and a processing module B, the processing module A includes a block A1 and a block A2, the blocks A1 and A2 include two convolutional layers, a normalization layer and an average pooling layer, the processing module B includes a block B1 and a block B2, the block B1 includes a channel attention module and a spatial attention module, and the block B2 includes three convolutional layers and a maximum pooling layer;

[0089] The output layer includes error reconstruction and activation function. The error reconstruction is used to perform reverse error analysis on the material category parameters to determine whether the error threshold is met. If not, retraining is performed. If so, the material type is output according to the activation function.

[0090] See also Figure 3 , a flow chart of the device adjustment logic steps of an embodiment of the present invention, the device adjustment logic includes:

[0091] The preset parameter mapping table is queried according to the material type to determine the initial crushing parameters, which include crushing force, rotation speed and feed speed. The parameter mapping table is pre-set based on a large amount of experimental data and empirical rules, which can provide a reasonable crushing parameter for different types of materials, provide a basis for subsequent optimization, reduce the time of parameter setting, and improve production efficiency.

[0092] The fitness of the initial crushing parameters is calculated based on the crushing equipment data. The design of the fitness function comprehensively considers the equipment operation efficiency, energy consumption and material crushing effect. The fitness is iteratively optimized according to the genetic algorithm to calculate the optimal fitness of the initial crushing parameters. The fitness calculation provides a quantitative evaluation standard for subsequent parameter optimization to ensure that the optimization process can find the best balance point of crushing efficiency, energy consumption and crushing quality. The fitness calculation formula is:

[0093] f p =α1η c (X)-α2η e (X)+α3η q (X),

[0094] Among them, f p represents the fitness of the initial crushing parameters, X represents the initial crushing parameters, α1, α2 and α3 represent weight coefficients, which are set according to the actual production environment requirements, and η c (X) represents the crushing efficiency under the initial crushing parameters, which is related to the equipment processing capacity and the particle size distribution of the output material. e (X) represents the energy consumption under the initial crushing parameters, representing the power consumption of the equipment under the set parameters, η q (X) represents the crushing quality under the initial crushing parameters, which is related to the particle size and particle size distribution consistency of the finished product;

[0095] Fitness is an important basis for subsequent genetic operations. The level of fitness reflects the adaptability of the initial crushing parameters to the material. By mapping the optimization target, calculating the fitness of all initial crushing parameters, and calibrating the fitness through the linear calibration method, the emergence of super individuals can be prevented.

[0096] The iterative optimization includes selection operation, crossover operation and mutation operation. The selection operation retains excellent individuals or passes them on after genetic operation, and eliminates inferior individuals. The crossover operation replaces and reconstructs part of the genes of two parent chromosomes to produce two new daughter chromosomes. The mutation operation generates new individuals by changing part of the genes of the chromosomes.

[0097] The initial crushing parameters are dynamically adjusted according to the material characteristic vector, the best fitness and the initial crushing parameters, and the optimal crushing parameters are calculated. Through dynamic adjustment, the crushing equipment can adapt to the real-time changes in material characteristics, realize accurate optimization of parameters, and improve the crushing effect. The calculation formula for the optimal crushing parameters is:

[0098]

[0099] Among them, B c represents the optimal crushing parameter, F a Indicates the adjusted crushing force, N a Indicates the adjusted speed, V a Indicates the adjusted feed rate, f b represents the optimal fitness of the initial crushing parameters, F represents the initial crushing force, N represents the initial rotation speed, V represents the initial feed rate, ΔH represents the deviation value of the material hardness coefficient from the standard hardness coefficient, H co Indicates the material hardness coefficient, k H Indicates the adjustment coefficient of the material hardness coefficient characteristics, ΔW indicates the deviation of the material humidity ratio from the standard humidity ratio, k W The adjustment factor representing the material moisture ratio, W ra Indicates the material moisture ratio, k D Indicates the adjustment coefficient between the material particle size distribution and the standard particle size distribution, D 50 Represents the median value of the material particle size distribution, σ D represents the distribution deviation of the material particle size distribution, D represents the material particle size distribution, k ρ represents the adjustment coefficient between material density and standard density, ρ represents material density, k C represents the adjustment coefficient between the mineral components of the material and the standard mineral components, ΔC represents the deviation value between the mineral components of the material and the standard mineral components, and C represents the mineral components of the material;

[0100] By monitoring the crushing equipment operating data fed back by the sensor, the crushing equipment operating data is compared with the optimal crushing parameters. If the deviation is greater than the operating threshold, the crushing parameters of the crushing equipment are adjusted for the second time. The real-time monitoring and secondary adjustment functions ensure the high stability and reliability of the equipment during the production process. Even when the material properties or production environment change, the crushing equipment can maintain the best working condition.

[0101] The system can automatically select the appropriate graded crushing mode according to the hardness and particle size characteristics of the material, and control the crushing process to be divided into three stages: coarse crushing, medium crushing and fine crushing. The crushing parameters of each stage are independently optimized to ensure that the particle size of the final product reaches the optimal state. During the crushing process, the system can dynamically adjust the working parameters of the crushing equipment at all levels to achieve the optimal energy consumption. For example, under the premise of ensuring the crushing quality, the system can reduce energy consumption by reducing unnecessary crushing force and equipment idling time.

[0102] The intelligent screening module comprises:

[0103] The particle size monitoring unit is used to monitor the particle size distribution of each layer of materials during the screening process in real time;

[0104] The screening prediction unit is used to predict the particle size monitoring data, determine whether there is a blockage, and adjust the vibration frequency, amplitude and screen angle of the screening equipment according to the blockage situation;

[0105] Screen cleaning unit to remove deposits from the screening process;

[0106] The particle size monitoring strategy includes particle size distribution monitoring logic and material blockage prediction logic;

[0107] The particle size distribution monitoring logic is configured in the particle size monitoring unit, and the material blockage prediction logic is configured in the screening prediction unit.

[0108] The particle size distribution monitoring logic includes:

[0109] Collecting flow images during material screening by an optical camera, and preprocessing the flow images, wherein the preprocessing includes linear enhancement and noise removal;

[0110] Traverse each pixel in the preprocessed flow image, calculate the sum of the grayscale weighted differences between the pixel neighborhood and the pixel, compare the sum of the grayscale weighted differences with the binarization threshold, and if it is less than the binarization threshold, set the pixel to zero to obtain a particle binarization image;

[0111] The peak values ​​of the binary particle image are counted by Hough transform, the horizontal coordinates of the parallel lines are determined according to the peak values, the particle flow area is obtained according to the upper and lower boundary coordinates of the binary particle image and the horizontal coordinates of the parallel lines, all white pixels in the particle flow area are projected, and the flow particle image is extracted;

[0112] Marking the pixel edge point coordinates of each flow particle image, extracting the particle area feature, and calculating the particle flow feature according to the variance of the particle area feature;

[0113] Divide each flow particle image into sub-regions in an equidistant manner according to the horizontal and vertical directions, extract the area features of the sub-regions, and calculate the particle stability features according to the standard deviation of the area features of the sub-regions;

[0114] The particle flow characteristics and particle stability characteristics are fused through a 1×1 convolution kernel to calculate the particle uniformity characteristics;

[0115] Calculating a particle size distribution curve for each layer of sieve according to the uniform characteristics of the particles;

[0116] The calculation formula of the particle uniformity characteristic is:

[0117]

[0118] Among them, U c Indicates the uniformity of particles, T ci represents the particle flow characteristics, H represents the particle stability characteristics, μ represents the average projection matrix of white pixels in the powder flow area, T represents the matrix transpose, q represents the horizontal coordinate of the pixel of the flowing powder image, k represents the vertical coordinate of the pixel of the flowing particle image, Q represents the total number of pixels in the horizontal direction of the flowing particle image, K represents the total number of pixels in the vertical direction of the flowing particle image, I(q,k) represents the gray value of the flowing particle image at the position (q,k), and h I represents the average gray value of the flow particle image, f{·} represents the convolution kernel of size 1×1, Represents vector multiplication.

[0119] The material blockage prediction logic includes:

[0120] Vibration sensors, acceleration sensors and acoustic wave sensors distributed on each layer of the screening equipment can collect the vibration frequency, amplitude, material flow rate and acoustic wave signal intensity of each layer of materials in the screening process in real time;

[0121] Preprocess the collected vibration frequency, amplitude, material flow rate, acoustic wave signal, image data and laser reflection intensity data, including filtering, denoising and standardization. Use time series analysis methods to time-calibrate the processed data and establish a multi-dimensional time series data set.

[0122] Extract key characteristic parameters from the preprocessed data, including the vibration frequency change rate, amplitude change rate, material flow rate fluctuation amplitude, acoustic signal intensity fluctuation, area ratio of material accumulation in the image, and laser reflection intensity change;

[0123] A material blockage prediction model is constructed based on historical screening data. The current key characteristic parameters are input into the trained prediction model. The material blockage probability of each layer of the screen is calculated in real time. According to the blockage probability output by the model, it is determined whether there is a material blockage trend and the corresponding prediction results are output.

[0124] The grinding control module comprises:

[0125] Dust change monitoring unit, used to monitor the dust change distribution of materials in the grinding process in real time through a high-precision laser particle size analyzer;

[0126] The equipment control unit is used to dynamically adjust the working pressure and speed of the grinding equipment based on the real-time data provided by the dust conversion monitoring unit, including:

[0127] Use PID control algorithm to adjust the pressure and speed of the grinding equipment through closed-loop feedback;

[0128] When abnormal dust fluctuations are detected, the grinding roller pressure or grinding disc speed is automatically adjusted.

[0129] The intelligent transport module comprises:

[0130] Material flow monitoring unit, used to monitor the material flow and conveying status in real time through the material flow sensor and weight sensor installed on the conveyor belt;

[0131] The conveying parameter dynamic adjustment unit is used to automatically adjust the speed and inclination of the conveyor belt according to the data provided by the material flow monitoring unit;

[0132] When the material flow is detected to be too large or too small, the conveyor belt speed is automatically adjusted to avoid material accumulation or poor conveying.

[0133] When the conveying inclination angle is not suitable for the current material characteristics, the conveyor belt inclination angle is automatically adjusted according to the physical characteristics of the material to ensure the conveying efficiency;

[0134] The conveying path optimization unit is used to intelligently select the optimal conveying path based on real-time material flow data to avoid congestion and unnecessary energy consumption.

[0135] The feedback optimization module comprises:

[0136] Finished product quality monitoring unit, used to monitor the particle size, humidity and density of finished product materials in real time according to the quality inspection equipment;

[0137] The parameter optimization logic unit is used to analyze whether the working parameters of each module in the current production process meet expectations based on the data fed back by the finished product quality monitoring unit. When the quality of the finished product deviates, the system optimizes and adjusts the working parameters of each module.

[0138] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. The SCM sand making process optimization system based on the Internet of Things is characterized by: The system comprises: Adaptive crushing module, intelligent screening module, grinding control module, intelligent conveying module and feedback optimization module; The adaptive crushing module is configured with a crushing optimization strategy, which is used to adjust the working parameters of the crushing equipment in real time according to the material characteristics; The intelligent screening module is equipped with a particle size monitoring strategy, which is used to monitor the particle size of the material and predict the material clogging trend during the screening process; The grinding control module is used to adjust the pressure and speed of the grinding equipment according to the change of the particle size of the material during the grinding process; The intelligent conveying module is used to monitor the material flow and conveying status and adjust the conveyor belt speed and inclination; The feedback optimization module is used to optimize the working parameters of the system modules according to the quality of the finished product.

2. According to the SCM sand making process optimization system based on the Internet of Things according to claim 1, it is characterized in that: The adaptive crushing module comprises: A material identification unit, used to collect physical property data of the material and identify the type of the material according to the physical property data; A crushing equipment adjustment unit, used to adjust the working parameters of the crushing equipment according to the material type output by the material identification unit; The crushing optimization strategy includes material identification logic and equipment adjustment logic. The material identification logic is used to calculate the material feature vector according to the physical property data, train the material feature vector by building a feature classification network, and identify the type of material. The equipment adjustment logic is used to adjust the initial crushing parameters of the crushing equipment. The material identification logic is configured in the material identification unit, and the equipment adjustment logic is configured in the crushing equipment adjustment unit.

3. According to the SCM sand making process optimization system based on the Internet of Things according to claim 2, it is characterized in that: The device adjustment logic includes: Querying a preset parameter mapping table according to the material type to determine initial crushing parameters, wherein the initial crushing parameters include crushing force, rotation speed and feed speed; Calculating the fitness of the initial crushing parameters according to the crushing equipment data, iteratively optimizing the fitness according to the genetic algorithm, and calculating the optimal fitness of the initial crushing parameters; Dynamically adjusting the initial crushing parameters according to the material characteristic vector, the optimal fitness and the initial crushing parameters, and calculating the optimal crushing parameters; The crushing equipment operation data fed back by the monitoring sensor is compared with the optimal crushing parameters. If the deviation is greater than the operation threshold, the crushing parameters of the crushing equipment are adjusted for the second time.

4. According to the SCM sand making process optimization system based on the Internet of Things according to claim 3, it is characterized in that: The calculation formula of the optimal crushing parameters is: Among them, B c represents the optimal crushing parameter, F a Indicates the adjusted crushing force, N a Indicates the adjusted speed, V a Indicates the adjusted feed rate, f b represents the optimal fitness of the initial crushing parameters, F represents the initial crushing force, N represents the initial rotation speed, V represents the initial feed rate, ΔH represents the deviation value of the material hardness coefficient from the standard hardness coefficient, H co Indicates the material hardness coefficient, k H Indicates the adjustment coefficient of the material hardness coefficient characteristics, ΔW indicates the deviation of the material humidity ratio from the standard humidity ratio, k W The adjustment factor representing the material moisture ratio, W ra Indicates the material moisture ratio, k D Indicates the adjustment coefficient between the material particle size distribution and the standard particle size distribution, D 50 Represents the median value of the material particle size distribution, σ D represents the distribution deviation of the material particle size distribution, D represents the material particle size distribution, k ρ represents the adjustment coefficient between material density and standard density, ρ represents material density, k C It represents the adjustment coefficient between the mineral composition of the material and the standard mineral composition, ΔC represents the deviation value between the mineral composition of the material and the standard mineral composition, and C represents the mineral composition of the material.

5. According to the SCM sand making process optimization system based on the Internet of Things according to claim 1, it is characterized in that: The intelligent screening module comprises: The particle size monitoring unit is used to monitor the particle size distribution of each layer of materials during the screening process in real time; Screening prediction unit, used to predict the particle size monitoring data, determine whether there is a blockage, and adjust the vibration frequency, amplitude and screen angle of the screening equipment according to the blockage situation; Screen cleaning unit to remove deposits from the screening process; The particle size monitoring strategy includes particle size distribution monitoring logic and material blockage prediction logic; The particle size distribution monitoring logic is configured in the particle size monitoring unit, and the material blockage prediction logic is configured in the screening prediction unit.

6. The SCM sand making process optimization system based on the Internet of Things according to claim 5 is characterized in that: The particle size distribution monitoring logic includes: Collecting flow images during material screening by an optical camera, and preprocessing the flow images, wherein the preprocessing includes linear enhancement and noise removal; Traverse each pixel in the preprocessed flow image, calculate the sum of the grayscale weighted differences between the pixel neighborhood and the pixel, compare the sum of the grayscale weighted differences with the binarization threshold, and if it is less than the binarization threshold, set the pixel to zero to obtain a particle binarization image; The peak values ​​of the binary particle image are counted by Hough transform, the horizontal coordinates of the parallel lines are determined according to the peak values, the particle flow area is obtained according to the upper and lower boundary coordinates of the binary particle image and the horizontal coordinates of the parallel lines, all white pixels in the particle flow area are projected, and the flow particle image is extracted; Marking the pixel edge point coordinates of each flow particle image, extracting the particle area feature, and calculating the particle flow feature according to the variance of the particle area feature; Divide each flow particle image into sub-regions in an equidistant manner according to the horizontal and vertical directions, extract the area features of the sub-regions, and calculate the particle stability features according to the standard deviation of the area features of the sub-regions; The particle flow characteristics and particle stability characteristics are fused through a 1×1 convolution kernel to calculate the particle uniformity characteristics; The particle size distribution curve of each layer of the sieve is calculated according to the uniform characteristics of the particles.

7. The SCM sand making process optimization system based on the Internet of Things according to claim 5 is characterized in that: The material blockage prediction logic includes: Vibration sensors, acceleration sensors and acoustic wave sensors distributed on each layer of the screening equipment can collect the vibration frequency, amplitude, material flow rate and acoustic wave signal intensity of each layer of materials in the screening process in real time; Preprocess the collected vibration frequency, amplitude, material flow rate, acoustic wave signal, image data and laser reflection intensity data, including filtering, denoising and standardization. Use time series analysis methods to time-calibrate the processed data and establish a multi-dimensional time series data set. Extract key characteristic parameters from the preprocessed data, including the vibration frequency change rate, amplitude change rate, material flow rate fluctuation amplitude, acoustic signal intensity fluctuation, area ratio of material accumulation in the image, and laser reflection intensity change; A material blockage prediction model is constructed based on historical screening data. The current key characteristic parameters are input into the trained prediction model. The material blockage probability of each layer of the screen is calculated in real time. According to the blockage probability output by the model, it is determined whether there is a material blockage trend and the corresponding prediction results are output.

8. The SCM sand making process optimization system based on the Internet of Things according to claim 1 is characterized in that: The grinding control module comprises: Dust change monitoring unit, used to monitor the dust change distribution of materials in the grinding process in real time through a high-precision laser particle size analyzer; The equipment control unit is used to dynamically adjust the working pressure and speed of the grinding equipment based on the real-time data provided by the dust conversion monitoring unit, including: Use PID control algorithm to adjust the pressure and speed of the grinding equipment through closed-loop feedback; When abnormal dust fluctuations are detected, the grinding roller pressure or grinding disc speed is automatically adjusted.

9. The SCM sand making process optimization system based on the Internet of Things according to claim 1 is characterized in that: The intelligent transport module comprises: Material flow monitoring unit, used to monitor the material flow and conveying status in real time through the material flow sensor and weight sensor installed on the conveyor belt; The conveying parameter dynamic adjustment unit is used to automatically adjust the speed and inclination of the conveyor belt according to the data provided by the material flow monitoring unit; When the material flow is detected to be too large or too small, the conveyor belt speed is automatically adjusted to avoid material accumulation or poor conveying. When the conveying inclination angle is not suitable for the current material characteristics, the conveyor belt inclination angle is automatically adjusted according to the physical characteristics of the material to ensure the conveying efficiency; The conveying path optimization unit is used to intelligently select the optimal conveying path based on real-time material flow data to avoid congestion and unnecessary energy consumption.

10. The SCM sand making process optimization system based on the Internet of Things according to claim 1 is characterized in that: The feedback optimization module comprises: Finished product quality monitoring unit, used to monitor the particle size, humidity and density of finished product materials in real time according to the quality inspection equipment; The parameter optimization logic unit is used to analyze whether the working parameters of each module in the current production process meet expectations based on the data fed back by the finished product quality monitoring unit. When the quality of the finished product deviates, the system optimizes and adjusts the working parameters of each module.

Images