An intelligent conveying and warehousing system for ceramic tiles

Abstract

The present invention provides an intelligent conveying and warehousing system for ceramic tiles, which relates to the technical field of material conveying applications. The present invention numbers the conveying stages through a marking module to achieve precise tracking and improve the operating efficiency of the system; a data acquisition module monitors the state and energy consumption of ceramic tiles in real time to optimize resource allocation and reduce costs; a weight prediction module uses machine learning to predict the weight of ceramic tiles to improve automation and prediction accuracy; a threshold comparison module verifies the weight prediction to ensure product quality; a first correlation module analyzes the relationship between physical indicators and energy consumption to provide a basis for energy consumption management; an energy consumption construction module sets an expected energy consumption value to optimize energy use; an optimal energy consumption selection module adjusts the set value so as not to exceed the expected energy consumption to achieve energy conservation and cost optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of material conveying applications, and particularly to an intelligent conveying and warehousing system for ceramic tiles; Background Art

[0002] In the modern ceramic tile production industry, conveying and warehousing are two important links. Generally, the produced ceramic tiles need to be transported through equipment such as conveyor belts and then stored in a warehouse. However, traditional conveying and warehousing methods often have many problems, such as low efficiency, high energy consumption, poor accuracy, etc. For example, in the process of conveying ceramic tiles, due to the unknown weight of the ceramic tiles, it is difficult to control the energy consumption and the efficiency is low. In addition, inaccurate prediction of the weight of ceramic tiles will also cause troubles to subsequent warehousing, sorting and other operations;

[0003] In the prior art, an intelligent material conveying device with the publication number of CN217554958U includes a silo. A first scraper conveyor is arranged at the bottom of the silo. A filtering device is arranged at the outlet of the first scraper conveyor. The filtering device includes a first support. A first elevator is bolted to the inner wall of the first support. The top of the first elevator is fixedly connected with an electric three-way. The bottom of the electric three-way is fixedly connected with a conduit. The bottom of the conduit is fixedly connected with a single-cylinder sieve for filtering and screening the materials in the silo. The single-cylinder sieve is communicated with a storage device through a bottom connecting pipe. The storage device includes a second elevator. A fixing frame is fixedly connected to the side wall of the second elevator near the top position; this prior art can monitor the operation status of the system in real time, master production data, and reduce human operation errors; improve the system safety, and greatly reduce the equipment maintenance time and cost;

[0004] In the actual operation process, there are still some problems. On the one hand, the prediction accuracy of the physical indexes of ceramic tiles by the existing system still needs to be improved. Excessive errors will affect the overall performance and efficiency of the system. On the other hand, there are still some deficiencies in the control of energy consumption by the existing system, and it is impossible to effectively save energy; in addition, in the existing technology, the correlation between physical indexes and energy consumption is often ignored, which makes the optimization of the system have certain limitations; when there is a certain correlation between the weight of ceramic tiles and energy consumption, if the parameters of the conveying process can be adjusted according to this correlation, the performance and efficiency of the system will be further improved;

[0005] The above information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art; Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent conveying and warehousing system for ceramic tiles to solve the problems raised in the above background art;

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An intelligent conveying and warehousing system for tiles, specifically including:

[0009] Marking module: Number each conveying stage experienced by the conveyor belt to form a sequence {1, 2,..., i,..., n}, where i represents the index of the i-th conveying process, and n represents the total number of conveying processes;

[0010] Data acquisition module: Used to collect the first physical index data and the first energy consumption data of the tiles during the i-th conveying process. The first physical index data includes but is not limited to the directly measured weight of the tiles;

[0011] Weight prediction module: Used to obtain the vibration data generated by the tiles with known weights on the conveyor belt, extract the vibration characteristic data from the vibration data, train a machine learning model using the vibration characteristic data, and through this machine learning model, construct a vibration analysis model. This vibration analysis model is used to perform real-time analysis on the vibration data of tiles with unknown weights, so as to predict the weight of the tiles;

[0012] Threshold comparison module: Used to perform a threshold comparison between the directly measured tile weight result in the first physical index data and the tile weight indirectly predicted by the vibration analysis model to determine the final weight of the tiles;

[0013] Data preprocessing module: Used to preprocess the first physical index data and the first energy consumption data after obtaining them, remove outliers and noise, and perform standardization processing on the data;

[0014] First correlation module: Used to obtain the preprocessed first physical index data and the first energy consumption data, and perform correlation analysis on these two types of data to obtain a first correlation coefficient. The first correlation coefficient is used to evaluate the degree of association of the i-th conveying process;

[0015] Energy consumption construction module: Used to obtain the first energy consumption data of n conveying processes, perform calculation and analysis to obtain the total energy consumption value, and set the energy consumption expected value of the i-th conveying process according to the total energy consumption value;

[0016] Optimal energy consumption selection module: Used to set a preset threshold for the first correlation coefficient. If the first correlation coefficient is lower than the preset threshold, adjust the set value of the first physical index data to ensure that the energy consumption value of the i-th conveying process does not exceed its corresponding energy consumption expected value.

[0017] Furthermore, define the total energy consumption value as E, and the calculation formula is as follows:

[0018]

[0019] Among them, E represents the total energy consumption; w 1 , w 2 , w 3 are the positive weights of the conveying time, motor power, and conveyor belt tension respectively. is an exponential function used to process the motor power, and ln(1 + DZli) is a natural logarithmic function. is a cube root function used to process the conveying time. The smaller E is, the lower the energy consumption and the more efficient the conveying process; conversely, the larger E is, the higher the energy consumption and the less efficient the conveying process.

[0020] Define the expected energy consumption value Ei for the i-th conveying process as follows:

[0021]

[0022] Among them, Ei represents the expected energy consumption value for the i-th conveying process, which is an average value of the total energy consumption.

[0023] Furthermore, set the preset threshold of the first correlation coefficient. If the first correlation coefficient is lower than the preset threshold, adjust the set value of the first physical index data to ensure that the energy consumption value of the i-th conveying process does not exceed its corresponding expected energy consumption value. The specific content is as follows:

[0024] Set the preset threshold of Ri to 0.4. When Ri < 0.4, it indicates that the correlation degree between the physical index and the energy consumption data is relatively low and needs to be optimized.

[0025] If Ri is between 0 and 0.2, the adjustment strategy is to reduce the expected energy consumption by 20%. Specifically as follows:

[0026] Increase the conveying speed Svi to 120% of the current value;

[0027] Reduce the conveying distance Sdi to 80% of the current value;

[0028] Increase the processing capacity of the tile weight Zli to 150% of the current value;

[0029] If Ri is between 0.2 and 0.4, the adjustment strategy is to reduce the expected energy consumption by 10%. Specifically as follows:

[0030] Increase the conveying speed Svi to 110% of the current value;

[0031] Reduce the conveying distance Sdi to 90% of the current value;

[0032] Increase the processing capacity of the tile weight Zli to 120% of the current value.

[0033] Compared with the prior art, the beneficial effects of the present invention are as follows: The marking module numbers the conveying stages to achieve precise tracking and improve the operating efficiency of the system; the data acquisition module monitors the tile status and energy consumption in real time to optimize resource allocation and reduce costs; the weight prediction module uses machine learning to predict the tile weight, improving automation and prediction accuracy; the threshold comparison module verifies the weight prediction to ensure product quality; the first correlation module analyzes the relationship between physical indicators and energy consumption to provide a basis for energy consumption management; the energy consumption construction module sets the expected energy consumption value to optimize energy use; the optimal energy consumption selection module adjusts the set value not to exceed the expected energy consumption to achieve energy conservation and cost optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the overall module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] To make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the following further elaborates on the present invention in conjunction with specific embodiments;

[0036] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention pertains; the "first", "second" and similar terms used in the present invention do not represent any order, quantity or importance, but are only used to distinguish different components; the terms such as "including" or "comprising" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects; the terms such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect; the terms such as "upper", "lower", "left", "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly;

[0037] Embodiment 1:

[0038] Please refer to Figure 1 The present invention provides a technical solution:

[0039] An intelligent tile conveying and warehousing system, the conveying and warehousing system includes a conveyor belt, specifically including:

[0040] Marking module: Number each conveying stage experienced by the conveyor belt to form a sequence {1, 2,..., i,..., n}, where i represents the index of the i-th conveying process and n represents the total number of conveying processes;

[0041] Data acquisition module: used to collect the first physical index data and the first energy consumption data of the tiles during the i-th conveying process. The first physical index data includes but is not limited to the directly measured weight of the tiles;

[0042] Weight prediction module: used to obtain the vibration data generated by the tiles with known weights on the conveyor belt, extract the vibration characteristic data from the vibration data, train a machine learning model using the vibration characteristic data, and construct a vibration analysis model through this machine learning model. This vibration analysis model is used to perform real-time analysis on the vibration data of tiles with unknown weights, so as to predict the weight of the tiles;

[0043] Threshold comparison module: used to perform a threshold comparison between the directly measured tile weight result in the first physical index data and the tile weight indirectly predicted by the vibration analysis model, so as to determine the final weight of the tiles;

[0044] Data preprocessing module: used to perform preprocessing after obtaining the first physical index data and the first energy consumption data, remove outliers and noise, and perform standardization processing on the data;

[0045] First correlation module: used to obtain the preprocessed first physical index data and the first energy consumption data, and perform correlation analysis on these two types of data to obtain the first correlation coefficient. The first correlation coefficient is used to evaluate the degree of correlation of the i-th conveying process;

[0046] Energy consumption construction module: used to obtain the first energy consumption data of n conveying processes, perform calculation and analysis to obtain the total energy consumption value, and set the energy consumption expected value of the i-th conveying process according to the total energy consumption value;

[0047] Optimal energy consumption selection module: used to set a preset threshold for the first correlation coefficient. If the first correlation coefficient is lower than the preset threshold, adjust the set value of the first physical index data to ensure that the energy consumption value of the i-th conveying process does not exceed its corresponding energy consumption expected value.

[0048] Embodiment 2:

[0049] On the basis of Embodiment 1, it is further explained that the data preprocessing module specifically includes the following contents;

[0050] Removing outliers: Through statistical analysis, identify and remove obvious abnormal data points;

[0051] Using the mean and standard deviation, first calculate the mean μ and standard deviation σ of the data set, and then select the threshold 2σ. Any data points outside the range of [μ - 2σ, μ + 2σ] are regarded as outliers and should be removed from the data set;

[0052] Noise filtering: Apply the Kalman filter of the filtering technology or smooth the data curve;

[0053] Standardization processing: Normalize the data to a unified range (0, 1) to eliminate the influence between different dimensions;

[0054] A method to scale all features to the range (0, 1); for each value, apply the following formula: where Xmax and Xmin are the maximum and minimum values in the dataset respectively.

[0055] Example 3:

[0056] Based on Example 2, it is further explained that the first physical index data includes the tile weight, conveying distance, conveying speed, and tile volume, and the tile weight, conveying distance, conveying speed, and tile volume collected during the i-th transportation process are marked as Zli, Sdi, Svi, and Zji in sequence;

[0057] Tile weight:

[0058] Obtaining method: Use a weighing device, specifically, install a dynamic weighing sensor on the conveyor belt, which can measure the weight of the tile in real time when the tile passes through and can handle weighing during high-speed movement;

[0059] Unit: In kilograms (kg) or grams (g);

[0060] Determination method: Place the tile on the weighing device and read the displayed weight value;

[0061] Conveying distance:

[0062] Obtaining method: Determine by measuring the length of the conveying system, using a distance sensor or according to the designed length of the conveyor belt;

[0063] Unit: In meters (m);

[0064] Determination method: Measure the straight-line distance of the conveyor belt from the starting point to the ending point;

[0065] Conveying speed:

[0066] Obtaining method: Use a speed sensor or calculate by the rotational speed of the conveyor belt driving motor;

[0067] Unit: In meters per second (m / s) or meters per minute (m / min);

[0068] Determination method: Measure the moving distance of the conveyor belt within a unit time;

[0069] Tile volume:

[0070] Obtaining method: Calculate the volume by measuring the length, width, and thickness of the tile;

[0071] Unit: in cubic meters (m 3 ) or cubic centimeters (cm 3 );

[0072] Determination method: Use a ruler or measuring tool to measure the three dimensions of the tile, and then calculate the volume;

[0073] The first energy consumption data includes the conveying time, motor power, and conveyor belt tension, and the conveying time, motor power, and conveyor belt tension collected during the i-th transportation process are marked as Sti, Dpi, and DZli in sequence;

[0074] Conveying time:

[0075] Obtaining method: Record the start and end times of the conveying process through a timer or control system;

[0076] Unit: in seconds (s) or minutes (min);

[0077] Determination method: Calculate the total time of the conveying process;

[0078] Motor power:

[0079] Obtaining method: Measure the power consumption of the motor through a power meter or watt-hour meter;

[0080] Unit: in watts (W) or kilowatts (kW);

[0081] Determination method: Monitor the power output of the motor in real time;

[0082] Conveyor belt tension:

[0083] Obtaining method: Use a tension sensor to measure the tension of the conveyor belt during operation;

[0084] Unit: in newtons (N);

[0085] Determination method: Install a tension sensor at the key position of the conveyor belt to monitor the tension value in real time.

[0086] Example 4:

[0087] On the basis of Example 3, further illustrate that the vibration data generated by tiles of known weight on the conveyor belt is obtained, and the vibration characteristic data in the vibration data is extracted. The machine learning model is trained using the vibration characteristic data, and through this machine learning model, a vibration analysis model is constructed. This vibration analysis model is used to perform real-time analysis on the vibration data of tiles of unknown weight, so as to predict the weight of the tiles. The specific content includes the following:

[0088] Install highly sensitive acceleration sensors at the starting and ending positions of the conveyor belt. The acceleration sensor at the starting position of the conveyor belt is used to capture the vibration data of the tiles when they first enter the conveyor belt; the acceleration sensor at the ending position of the conveyor belt is used to capture the vibration data of the tiles when they are about to leave the conveyor belt; the acceleration sensors are connected to a data acquisition system to record the vibration data in real time;

[0089] Use a digital filter to preprocess the collected vibration data to remove noise and interference; the filter used in this embodiment includes a low-pass filter for removing high-frequency noise;

[0090] Obtain the vibration characteristic data of tiles with known weights to train a machine learning model, specifically using Support Vector Machine (SVM) or Random Forest (RF); during the training process, the vibration characteristic data is used as the input and the weight of the tiles is used as the output. This is prior art and will not be elaborated here;

[0091] Use the cross-validation method to verify the trained model and evaluate its prediction accuracy;

[0092] Model verification: In the training dataset, select a part for training and the remaining part for cross-validation. Cross-validation is a commonly used model verification method in prior art. It divides the original data into K groups. Then, the model will be trained and verified K times. Each time, one of the groups is selected as the validation set and the rest are used as the training set. In this way, all the data can go through training and verification once, and each time it is not repeated;

[0093] Adjust the model parameters according to the verification results. In this embodiment, the selection of the kernel function and the regularization parameter are used to optimize the model performance; by observing the performance of the model during the cross-validation process, find the parameters that need to be adjusted, such as the selection of the kernel function and the regularization parameter. Then, by adjusting these parameters, optimize the performance of the model; this step often requires multiple attempts and comparisons until the optimal parameter settings are found. This technical means is prior art and will not be elaborated;

[0094] Use the trained machine learning model to analyze the vibration data of tiles with unknown weights and predict the tile weights in real time.

[0095] Example Five:

[0096] Based on Example Four, further illustrate that compare the directly measured tile weight result in the first physical index data with the tile weight indirectly predicted by the vibration analysis model through a threshold to establish the final weight of the tiles, specifically including the following content:

[0097] 1) Obtain the predicted result of the tile weight and the directly measured tile weight data. Mark the directly measured tile weight as Wsensor, and mark the tile weight indirectly predicted by the vibration analysis model as Wvibration. Set the comparison threshold as ΔW. If |Wsensor - Wvibration| ≤ ΔW is satisfied, then take Wsensor as the finally determined tile weight. If not satisfied, then proceed to step 2);

[0098] 2) Correct Wsensor, and the correction formula is:

[0099] Wcorrected = Wsensor + β 1 ·Factor 1 +β 2 ·Factor 2 +β 3 ·Factor 3

[0100] In the above formula, Wcorrected is the corrected tile weight;

[0101] β 1 is the influence coefficient of the sensor performance on the difference; β 2 is the influence coefficient of the environmental factor on the difference; β 3 is the influence coefficient of the vibration analysis model error on the difference; Factor 1 is the correction factor of the sensor performance, Factor 2 is the correction factor of the environmental factor, Factor 3 is the correction factor of the vibration analysis model error;

[0102]

[0103] Among them, β 1 , β 2 , β 3 , Factor 1 , Factor 2 , Factor 3 , β 1 <β 2 <β 3 , β 1 , β 2 , β 3 are all determined by the expert group according to the experimental data and the results of regression analysis, Factor 1 <Factor 2 <Factor 3 , and can be adjusted according to the actual usage situation;

[0104] 3) Determine whether |Wcorrected - Wvibration| ≤ ΔW is satisfied. If it is satisfied, then use Wcorrected as the finally determined weight of the tile. If it is not satisfied, then use Wcorrected as the directly measured weight of the tile and re - correct it through step 2).

[0105] Example Six:

[0106] Based on Example Five, further explanation is given. Define the first correlation coefficient as Ri, and the mathematical formula is as follows:

[0107]

[0108] Where, Zli represents the weight of the tile in the i - th conveying process; Sdi represents the conveying distance in the i - th conveying process; Svi represents the conveying speed in the i - th conveying process; Zji represents the volume of the tile in the i - th conveying process;

[0109] Sti represents the conveying time in the i - th conveying process; Dpi represents the motor power in the i - th conveying process; DZli represents the conveyor belt tension in the i - th conveying process, and c2 is a positive adjustment constant term, 0.02 ≤ c2 ≤ 0.89;

[0110] a, b, c, d, e, f, g are positive weight coefficients, a < b < c < d < e < f < g, and a + b + c + d + e + f + g = 1, which need to be determined through experiments or experience according to the actual situation;

[0111] The value range of Ri is (0, 1);

[0112] In this embodiment, the weight of the tile is divided at 30 kg. If it is greater than 30 kg, it is defined as "larger", and if it is less than 30 kg, it is defined as "lighter";

[0113] Conveying distance: Divided at 50 m. If it is greater than 50 m, it is defined as "longer", and if it is less than 50 m, it is defined as "shorter";

[0114] Conveying speed: Divided at 2 m / s. If it is greater than 2 m / s, it is defined as "faster", and if it is less than 2 m / s, it is defined as "slower";

[0115] Tile volume: Divided at 0.015 m³. If it is greater than 0.015 m³, it is defined as "larger", and if it is less than 0.015 m³, it is defined as "smaller";

[0116] Conveying time: Divided at 10 minutes. If it is greater than 10 minutes, it is defined as "longer", and if it is less than 10 minutes, it is defined as "shorter";

[0117] Motor power: Taking 5 kW as the dividing point, greater than 5 kW is defined as "higher", and less than 5 kW is defined as "lower".

[0118] Conveyor belt tension: Taking 10 N as the dividing point, greater than 10 N is defined as "higher", and less than 10 N is defined as "lower".

[0119] The above dividing values are adjusted by the expert group according to the actual situation and will not be elaborated here.

[0120] When the weight of the ceramic tile is relatively large, the value range of the weight a is from 0.3 to 0.4. And when the conveying distance is relatively long, the influence of the ceramic tile weight on energy consumption increases significantly.

[0121] In a specific scenario, assume that the weight a of the ceramic tile weight Zli is determined to be 35%. Based on this determined value, the proportion of the ceramic tile weight Zli in the first correlation coefficient Ri is 35%, which means that when calculating Ri, the influence of the ceramic tile weight Zli is relatively large. By increasing the weight of the ceramic tile, the influence of the ceramic tile weight on energy consumption can be more accurately reflected, thus optimizing the conveying process.

[0122] When the weight of the ceramic tile is relatively light, the percentage range of the weight a of the ceramic tile weight Zli is from 10% to 20%. And when the conveying distance is relatively short, the influence of the ceramic tile weight on energy consumption is relatively small.

[0123] In a specific scenario, assume that the weight Zli of the ceramic tile weight Zli is determined to be 15%. Based on this determined value, the proportion of the ceramic tile weight Zli in the first correlation coefficient Ri is 15%, which means that when calculating Ri, the influence of the ceramic tile weight Zli is relatively small. By reducing the weight of the ceramic tile, the influence of the ceramic tile weight on energy consumption can be more accurately reflected, thus optimizing the conveying process.

[0124] When the conveying distance is relatively long, the percentage range of the weight b of the conveying distance Sdi is from 20% to 30%, and the influence of the conveying distance on energy consumption increases significantly.

[0125] In a specific scenario, assume that the weight b of the conveying distance Sdi is determined to be 25%. Based on this determined value, the proportion of the conveying distance Sdi in the first correlation coefficient Ri is 25%, which means that when calculating Ri, the influence of the conveying distance Sdi is relatively large. By increasing the weight of the conveying distance, the influence of the conveying distance on energy consumption can be more accurately reflected, thus optimizing the conveying process.

[0126] When the conveying distance is relatively short, the percentage range of the weight b of the conveying distance Sdi is from 5% to 15%, and the influence of the conveying distance on energy consumption is relatively small.

[0127] In a specific scenario, assume that the weight b of the conveying distance Sdi is determined to be 10%; based on this determined value, the proportion of the conveying distance Sdi in the first correlation coefficient Ri is 10%, which means that the influence of the conveying distance Sdi is relatively small when calculating Ri; by reducing the weight of the conveying distance, the influence of the conveying distance on energy consumption can be more accurately reflected, thereby optimizing the conveying process;

[0128] When the conveying speed is relatively fast, the percentage range of the weight c of the conveying speed Svi is 15% to 25%, and the influence of the conveying speed on energy consumption increases significantly;

[0129] In a specific scenario, assume that the weight c of the conveying speed Svi is determined to be 20%; based on this determined value, the proportion of the conveying speed Svi in the first correlation coefficient Ri is 20%, which means that the influence of the conveying speed Svi is relatively large when calculating Ri; by increasing the weight of the conveying speed, the influence of the conveying speed on energy consumption can be more accurately reflected, thereby optimizing the conveying process;

[0130] When the conveying speed is relatively slow, the percentage range of the weight c of the conveying speed Svi is 5% to 15%, and the influence of the conveying speed on energy consumption is relatively small;

[0131] In a specific scenario, assume that the weight c of the conveying speed Svi is determined to be 10%; based on this determined value, the proportion of the conveying speed Svi in the first correlation coefficient Ri is 10%, which means that the influence of the conveying speed Svi is relatively small when calculating Ri; by reducing the weight of the conveying speed, the influence of the conveying speed on energy consumption can be more accurately reflected, thereby optimizing the conveying process;

[0132] When the tile volume is relatively large, the percentage range of the weight d of the tile volume Zji is 10% to 20%, and the influence of the tile volume on energy consumption increases significantly;

[0133] In a specific scenario, assume that the weight d of the tile volume Zji is determined to be 15%; based on this determined value, the proportion of the tile volume Zji in the first correlation coefficient Ri is 15%, which means that the influence of the tile volume Zji is relatively large when calculating Ri; by increasing the weight of the tile volume, the influence of the tile volume on energy consumption can be more accurately reflected, thereby optimizing the conveying process;

[0134] When the tile volume is relatively small, the percentage range of the weight d of the tile volume Zji is 5% to 15%, and the influence of the tile volume on energy consumption is relatively small;

[0135] In a specific scenario, assume that the weight d of the tile volume Zji is determined to be 10%; based on this determined value, the proportion of the tile volume Zji in the first correlation coefficient Ri is 10%, which means that the influence of the tile volume Zji is relatively small when calculating Ri; by reducing the weight of the tile volume, the influence of the tile volume on energy consumption can be more accurately reflected, thereby optimizing the conveying process;

[0136] When the conveying time is long, the percentage range of the weight e of the conveying time Sti is 15% to 25%; the influence of the conveying time on energy consumption increases significantly;

[0137] In a specific scenario, assume that the weight e of the conveying time Sti is determined to be 20%; based on this determined value, the proportion of the conveying time Sti in the first correlation coefficient Ri is 20%, which means that the influence of the conveying time Sti is relatively large when calculating Ri; by increasing the weight of the conveying time, the influence of the conveying time on energy consumption can be more accurately reflected, thereby optimizing the conveying process;

[0138] When the conveying time is short, the percentage range of the weight e of the conveying time Sti is 5% to 15%; the influence of the conveying time on energy consumption is relatively small;

[0139] In a specific scenario, assume that the weight e of the conveying time Sti is determined to be 10%; based on this determined value, the proportion of the conveying time Sti in the first correlation coefficient Ri is 10%, which means that the influence of the conveying time Sti is relatively small when calculating Ri; by reducing the weight of the conveying time, the influence of the conveying time on energy consumption can be more accurately reflected, thereby optimizing the conveying process;

[0140] When the motor power is high, the percentage range of the weight f of the motor power Dpi is 15% to 25%, and the influence of the motor power on energy consumption increases significantly;

[0141] In a specific scenario, assume that the weight f of the motor power Dpi is determined to be 20%; based on this determined value, the proportion of the motor power Dpi in the first correlation coefficient Ri is 20%, which means that the influence of the motor power Dpi is relatively large when calculating Ri; by increasing the weight of the motor power, the influence of the motor power on energy consumption can be more accurately reflected, thereby optimizing the conveying process;

[0142] When the motor power is low, the percentage range of the weight f of the motor power Dpi is 5% to 15%; the influence of the motor power on energy consumption is relatively small;

[0143] In a specific scenario, assume that the weight f of the motor power Dpi is determined to be 10%; based on this determined value, the proportion of the motor power Dpi in the first correlation coefficient Ri is 10%, which means that the influence of the motor power Dpi is relatively small when calculating Ri; by reducing the weight of the motor power, the influence of the motor power on energy consumption can be more accurately reflected, thereby optimizing the conveying process;

[0144] When the conveyor belt tension is high, the percentage range of the weight g of the conveyor belt tension DZli is 15% to 25%; the influence of the conveyor belt tension on energy consumption increases significantly;

[0145] In a specific scenario, assume that the weight g of the conveyor belt tension DZli is determined to be 20%; based on this determined value, the proportion of the conveyor belt tension DZli in the first correlation coefficient Ri is 20%, which means that the influence of the conveyor belt tension DZli is relatively large when calculating Ri; by increasing the weight of the conveyor belt tension, the influence of the conveyor belt tension on energy consumption can be more accurately reflected, thereby optimizing the conveying process;

[0146] When the conveyor belt tension is low, the percentage range of the weight g of the conveyor belt tension DZli is 5% to 15%; the influence of the conveyor belt tension on energy consumption is relatively small;

[0147] In a specific scenario, assume that the weight g of the conveyor belt tension DZli is determined to be 10%; based on this determined value, the proportion of the conveyor belt tension DZli in the first correlation coefficient Ri is 10%, which means that the influence of the conveyor belt tension DZli is relatively small when calculating Ri; by reducing the weight of the conveyor belt tension, the influence of the conveyor belt tension on energy consumption can be more accurately reflected, thereby optimizing the conveying process;

[0148] When Ri is closer to 0, it indicates that the degree of correlation between the physical index and the energy consumption data is lower, and the conveying process needs to be optimized;

[0149] When Ri is closer to 1, it indicates that the degree of correlation between the physical index and the energy consumption data is higher, and the conveying process is more efficient;

[0150] When Ri is between 0 and 0.2, it indicates that the degree of correlation between the physical index and the energy consumption data is extremely low; this means that there is a large amount of energy waste or inefficient processes in the conveying process; in this case, it is necessary to review the entire conveying process from beginning to end, identify the inefficient links, and seek improvement solutions; it is necessary to consider replacing with high-efficiency equipment, or improving the process flow, or retraining the operators;

[0151] When Ri is between 0.2 and 0.4, it indicates that the correlation degree between the physical index and the energy consumption data is relatively low; in this case, although the transportation process still needs to be optimized, a comprehensive reform is not required; starting from the part with poor physical indicators, if the correlation coefficient of speed is low, it is necessary to consider increasing the transportation speed or optimizing the control strategy of the transportation speed;

[0152] When Ri is between 0.4 and 0.6, it indicates that the correlation degree between the physical index and the energy consumption data is average; in this case, partial optimization of the transportation process is required; through more refined data analysis, find out the situations where the energy consumption is high under certain specific conditions, and then optimize for these situations;

[0153] When Ri is between 0.6 and 0.8, it indicates that the correlation degree between the physical index and the energy consumption data is relatively high; at this time, some details need to be optimized. Through refined energy consumption monitoring, find small fluctuations in energy consumption, and then adjust the equipment parameters to make the energy consumption more stable;

[0154] When Ri is between 0.8 and 1, it indicates that the correlation degree between the physical index and the energy consumption data is very high, and the transportation process is already very efficient at this time; but in order to achieve higher efficiency, some fine-tuning can be carried out. Through more refined data analysis, find small-scale but frequent energy consumption fluctuations, and then optimize the control strategy to reduce these fluctuations.

[0155] Example Seven:

[0156] On the basis of Example Six, it is further explained that the total energy consumption value is defined as E, and the calculation formula is as follows:

[0157]

[0158] Among them, E represents the total energy consumption; w 1 、w 2 、w 3 are the positive weights of the transportation time, motor power, and conveyor belt tension respectively, and w 1 +w 2 +w 3 =1, w 1 <w 2 <w 3 The positive weight indicates that the weight is a positive number, and these weights are set according to the actual situation, based on the statistical analysis of historical data or the expert's experience judgment;

[0159] is an exponential function used to process the motor power because the influence of the motor power on the total energy consumption is exponential;

[0160] ln(1 + DZli) is the natural logarithm function. Adding 1 is to avoid the situation where the logarithmic function cannot be calculated when the conveyor belt tension DZli is 0. This function is used to process the conveyor belt tension;

[0161] is the cube root function and is used to process the conveying time because the influence of the conveying time on the total energy consumption is at the cube root level;

[0162] The smaller E is, the lower the energy consumption and the more efficient the conveying process; conversely, the larger E is, the higher the energy consumption and the less efficient the conveying process;

[0163] Define the expected energy consumption value Ei for the i-th conveying process as follows:

[0164]

[0165] Among them, Ei represents the expected energy consumption value for the i-th conveying process and is an average value of the total energy consumption.

[0166] Example Eight:

[0167] Based on Example Seven, further illustrate. Set the preset threshold of the first correlation coefficient. If the first correlation coefficient is lower than the preset threshold, adjust the set value of the first physical index data so that the energy consumption value of the i-th conveying process is within the corresponding expected energy consumption value. The specific content includes the following:

[0168] Set the preset threshold of Ri to 0.4. When Ri < 0.4, it means that the degree of correlation between the physical index and the energy consumption data is relatively low and needs to be optimized; this threshold is determined based on historical data analysis and is aimed at distinguishing the conveying processes with poor efficiency;

[0169] If Ri is between 0 and 0.2, the adjustment strategy is as follows:

[0170] Increase the conveying speed Svi to 120% of the current value to improve efficiency;

[0171] Reduce the conveying distance Sdi to 80% of the current value to reduce unnecessary length by optimizing the path;

[0172] Increase the processing capacity of the tile weight Zli to 150% of the current value by upgrading equipment or improving the process;

[0173] Increasing Svi will directly improve the conveying efficiency, and it is expected to reduce the impact on the total energy consumption by 10%;

[0174] Reducing Sdi helps to reduce energy consumption, and the impact is to reduce energy consumption by 5%;

[0175] Increasing Zli represents higher batch processing efficiency and reduces the energy consumption per unit product. It is expected to reduce energy consumption by 5%;

[0176] The above adjustment reduces the expected energy consumption by 20%;

[0177] If Ri is between 0.2 and 0.4, the adjustment strategy is as follows:

[0178] Increase the conveying speed Svi to 110% of the current value to slightly improve the efficiency;

[0179] Reduce the conveying distance Sdi to 90% of the current value and reduce part of the length by fine-tuning the path;

[0180] Increase the processing capacity of the tile weight Zli to 120% of the current value by optimizing the operation process;

[0181] Increasing Svi improves the conveying efficiency, and the expected impact on the total energy consumption is 6%;

[0182] Reducing Sdi reduces the energy consumption by shortening the distance, and the expected impact on the energy consumption is 2%;

[0183] Increasing Zli improves the batch efficiency, is expected to reduce the energy consumption per unit product, and the expected impact on the energy consumption is 2%;

[0184] The above adjustment reduces the expected energy consumption by 10%;

[0185] The increase in the speed Svi significantly improves the conveying efficiency because a high speed means that more products can be processed in the same time, thus spreading the energy consumption per single tile;

[0186] The reduction of the distance Sdi directly affects the calculation of the energy consumption because less energy is consumed for short-distance conveying;

[0187] The increase in the tile weight Zli has a significant impact on the production efficiency because a larger batch can more effectively spread the energy consumption of equipment startup and operation.

[0188] Example Nine:

[0189] On the basis of Example Eight, it is further illustrated that in this example, this system uses the optimal energy consumption selection module to optimize the production process to achieve the goal of minimizing energy consumption and improving production efficiency;

[0190] In the test preparation stage, a threshold value of the associated number Ri is analyzed from the historical data. This threshold value can clearly distinguish between low-efficiency and high-efficiency conveying processes. The set Ri threshold value is 0.4. When the actual Ri value is lower than this threshold value, it means that the current production process has a low correlation with the energy consumption and needs to be optimized;

[0191] The weighting factors a, b, c, d, e, f, g are determined through experiments or experience to balance the influence weights of various physical indicators in the total energy consumption, and these weighting coefficients remain unchanged in each optimization adjustment;

[0192] It is expected that through the above optimization strategies, the efficiency of the production process can be improved and the energy consumption can be minimized to the greatest extent;

[0193] The following is the data table obtained after five tests:

[0194]

[0195]

[0196] The data analysis of the table is as follows:

[0197] By presetting the threshold of the correlation coefficient Ri and combining specific physical indicators, such as the conveying speed Svi, the conveying distance Sdi, and the tile weight Zli for adjustment, the conveying process is optimized, so that the energy consumption value of each conveying process falls within the expected value of the corresponding energy consumption;

[0198] 1. The energy consumption is significantly reduced:

[0199] From Test 1 to Test 5, the actual energy consumption E decreased from 150 kWh to 100 kWh, and the expected energy consumption Ei decreased from 130 kWh to 90 kWh. This indicates that through the adjustment strategy of the present invention, the energy consumption is reduced by 33.33%;

[0200] 2. The effectiveness and adaptability of the adjustment strategy:

[0201] The process of gradually approaching the preset threshold of 0.4 for the Ri value by adjusting Svi, Sdi, and Zli demonstrates the adaptability and effectiveness of the adjustment strategy; this process of gradual adjustment and optimization reflects the innovation and novelty of the present invention;

[0202] 3. The matching degree between the expected and actual energy consumption values is improved:

[0203] As the tests proceed, the gap between the actual energy consumption and the expected energy consumption gradually decreases, indicating that the coincidence degree between the expected calculation and the actual operation is continuously improved, which further verifies the accuracy and reliability of the formula and the adjustment strategy;

[0204] The increase in the conveying speed Svi has a significant impact on the reduction of energy consumption; from Test 1 to Test 5, Svi gradually increases, and the total energy consumption significantly decreases; this is because increasing the conveying speed can complete the same amount of work in a shorter time, thereby reducing energy consumption;

[0205] The reduction of the conveying distance Sdi is closely related to the reduction of energy consumption; by optimizing the conveying path and reducing unnecessary conveying distance, the energy consumption is directly reduced, which reflects the high efficiency of the strategy of the present invention;

[0206] The increased processing capacity of the tile weight Zli means that more tiles can be processed at a time, which not only improves the production efficiency, but also means that the energy consumption per kilogram of tiles is reduced. The resulting reduction in energy consumption further verifies the scientificity and rationality of the adjustment strategy;

[0207] After the adjustment by the strategy of the present invention, not only the energy consumption is significantly reduced, but also the energy consumption value of each conveying process can be ensured to fall within the expected energy consumption value, which reflects the specific technical effect in the implementation of the present invention.

[0208] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation;

[0209] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination; when implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product; those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware; whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution;

[0210] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment;

[0211] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all of them should be covered within the protection scope of this application.

Claims

1. An intelligent tile conveying and warehousing system, characterized in that: Specifically include: Marking module: Number each conveying stage experienced by the conveyor belt to form a sequence {1,2,...i,...,n}, where i represents the index of the i-th conveying process and n represents the total number of conveying processes; Data acquisition module: used for collecting first physical index data and first energy consumption data of the tiles during the i-th transportation process, wherein the first physical index data includes but is not limited to directly measured weight of the tiles; Weight prediction module: used to obtain the vibration data generated by tiles of known weight on the conveyor belt, extract the vibration feature data in the vibration data, train the machine learning model with the vibration feature data, and build a vibration analysis model through this machine learning model. The vibration analysis model is used to perform real-time analysis on the vibration data of tiles of unknown weight, so as to predict the weight of the tiles; Threshold comparison module: used for comparing the weight result of the tile directly measured in the first physical indicator data with the weight of the tile indirectly predicted by the vibration analysis model to establish the final weight of the tile; Data preprocessing module: used to obtain the first physical indicator data and the first energy consumption data, perform preprocessing, remove abnormal values ​​and noise, and standardize the data; A first correlation module: used to obtain the pre-processed first physical indicator data and the first energy consumption data, and perform correlation analysis on the two types of data to obtain a first correlation coefficient, wherein the first correlation coefficient is used to evaluate the correlation degree of the i-th transport process; Energy consumption building module: used to obtain the first energy consumption data of the n-th transportation process, perform calculation and analysis, obtain the total energy consumption value, and set the expected energy consumption value of the i-th transportation process according to the total energy consumption value; The total energy consumption value is defined as E, and the calculation formula is as follows: Where E represents the total energy consumption; w1, w2, and w3 are the positive weights of conveying time, motor power, and conveyor belt tension, respectively. It is an exponential function used to process motor power, ln(1+DZl i ) is the natural logarithm function, It is a cube root function, which is used to process the transportation time. The smaller E is, the lower the energy consumption is and the more efficient the transportation process is. On the contrary, the larger E is, the higher the energy consumption is and the less efficient the transportation process is. Define the expected energy consumption value E of the i-th transport process i as follows: Among them, E i It represents the expected value of energy consumption in the i-th transport process, which is an average value of the total energy consumption; Optimal energy consumption selection module: used to set a preset threshold value of the first correlation coefficient. If the first correlation coefficient is lower than the preset threshold value, the first physical indicator data setting value will be adjusted to ensure that the energy consumption value of the i-th conveying process does not exceed its corresponding expected energy consumption value.

2. According to claim 1, the intelligent tile conveying and warehousing system is characterized by: The first physical indicator data includes tile weight, conveying distance, conveying speed, and tile volume, and the tile weight, conveying distance, conveying speed, and tile volume collected during the i-th transportation process are marked as Zl in sequence. i , Sd i 、Sv i 、Zj i ; The first energy consumption data includes the transport time, motor power, and conveyor belt tension, and the transport time, motor power, and conveyor belt tension collected during the i-th transport are marked as St i 、Dp i ,DZl i .

3. According to claim 2, the intelligent tile conveying and warehousing system is characterized by: The predicted weight of the tile specifically includes the following contents: Highly sensitive acceleration sensors are installed at the starting and ending points of the conveyor belt. The acceleration sensors are connected to the data acquisition system to record vibration data in real time. Use digital filters to pre-process the collected vibration data to remove noise and interference; Extract features from the preprocessed vibration data and obtain the vibration feature data of tiles with known weight to train the machine learning model. During the training process, the vibration feature data is used as input and the weight of the tile is used as output. The trained model was verified using the cross-validation method to evaluate its prediction accuracy. The model parameters were adjusted based on the verification results, and the vibration data of tiles of unknown weight were analyzed using the trained machine learning model to predict the tile weight in real time.

4. The intelligent tile conveying and warehousing system according to claim 3 is characterized by: The step of comparing the weight of the tile directly measured in the first physical indicator data with the weight of the tile indirectly predicted by the vibration analysis model by threshold value to establish the final weight of the tile specifically includes the following: 1) Obtain the predicted results of tile weight and the directly measured tile weight data, and mark the directly measured tile weight as W sensor , the tile weight indirectly predicted by the vibration analysis model is marked as W vibration , set the comparison threshold to ΔW, if |W sensor -W vibration |≤ΔW, then W sensor As the final determined tile weight, if it is not satisfied, proceed to step 2); 2) For W sensor Make corrections, the correction formula is: W corrected =W sensor +β1·Factor1+β2·Factor2+β3·Factor3 In the above formula, W corrected is the corrected tile weight; β1 is the influence coefficient of sensor performance on the difference; β2 is the influence coefficient of environmental factors on the difference; β3 is the influence coefficient of vibration analysis model error on the difference; Factor1 is the correction factor of sensor performance, Factor2 is the correction factor of environmental factors, and Factor3 is the correction factor of vibration analysis model error; 3) Determine whether |W is satisfied corrected -W vibration |≤ΔW, if satisfied, then W corrected As the final tile weight, if it is not satisfied, then W corrected As the tile weight is directly measured, it is corrected again through step 2).

5. The intelligent tile conveying and warehousing system according to claim 4 is characterized by: Define the first correlation coefficient as R i , the mathematical formula is as follows: Among them, Zl i represents the weight of tiles during the i-th transportation process; Sd i Sv represents the transport distance in the i-th transport process; i represents the conveying speed during the i-th conveying process; Zj i represents the volume of tiles during the i-th transportation process; St i Denotes the delivery time during the i-th delivery process; Dp i represents the motor power during the i-th conveying process; DZl i represents the conveyor belt tension during the i-th conveying process, c2 is a positive adjustment constant; a, b, c, d, e, f, g are positive weight coefficients, R i The value range of is (0,1).

6. The intelligent tile conveying and warehousing system according to claim 5 is characterized by: The preset threshold of the first correlation coefficient is set. If the first correlation coefficient is lower than the preset threshold, the first physical indicator data setting value will be adjusted to ensure that the energy consumption value of the i-th transportation process does not exceed its corresponding energy consumption expected value, specifically including the following contents: Setting R i The preset threshold is 0.

4. i When <0.4, it means that the correlation between physical indicators and energy consumption data is low and needs to be optimized; If R i Between 0 and 0.2, the adjustment strategy is to reduce the expected energy consumption by 20% as follows: Increase the conveying speed Sv i to 120% of the current value; Reduce the conveying distance Sd i to 80% of the current value; Increase tile weight Zl i processing capacity to 150% of the current value; If R i Between 0.2 and 0.4, the adjustment strategy is to reduce the expected energy consumption by 10%, as follows: Increase the conveying speed Sv i to 110% of the current value; Reduce the conveying distance Sd i to 90% of the current value; Increase tile weight Zl i processing capacity to 120% of the current value.

Images