Particle cargo loading weight control method, device and equipment and storage medium

Abstract

The invention provides a particle cargo loading weight control method, device and equipment and a storage medium, and relates to the technical field of weighing control, and the method comprises the steps: continuously monitoring the latest target difference value when the target difference value between the real-time loading weight and the target loading weight is not smaller than a preset difference value threshold value; after it is monitored that the target difference value is smaller than a preset difference value threshold value, the real-time granularity and the real-time humidity of the loaded granular goods are continuously obtained, a gate closing trigger threshold value is calculated, whether the current target difference value is smaller than or equal to the current gate closing trigger threshold value or not is judged, if yes, a gate is closed, and if not, a new gate closing trigger threshold value and a new target difference value are continuously calculated; and comparing until the current target difference value is judged to be smaller than or equal to the current gate closing trigger threshold value. Therefore, a quantitative feeder and a quantitative bin are not needed, and the control precision of the loading weight of the granular goods is improved under the existing limited conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of weighing control, and in particular to a method, device, equipment and storage medium for controlling the loading weight of granular cargo. Background Art

[0002] At present, when loading granular goods such as coal and ore, the method of repeatedly opening and closing the gate at the tail feeding stage is used to try to accurately control the loading weight of granular goods. However, this method often results in overweight. Although the accuracy of loading weight can be improved by installing quantitative feeders and quantitative bins, in some traditional loading stations, due to relevant conditions, there are no quantitative bins and it is impossible to add quantitative feeders.

[0003] Based on this, how to improve the control accuracy of the loading weight of granular cargo under the existing restricted conditions has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of this, in order to solve the above technical problems, the present invention provides a method, device, equipment and storage medium for controlling the loading weight of granular cargo.

[0005] The present invention adopts the following technical solution: In a first aspect, the present invention provides a method for controlling the loading weight of a granular cargo, comprising: Obtaining basic information of the vehicle, wherein the basic information includes a target loading weight; After the vehicle compartment is placed on a track scale as a whole, obtaining the real-time loading weight of the vehicle; Calculating a target difference between the real-time loading weight and the target loading weight; Determine whether the target difference is less than a preset difference threshold; If the target difference is not less than the preset difference threshold, jump to the step of obtaining the real-time loading weight of the vehicle; If the target difference is less than the preset difference threshold, the real-time particle size and real-time humidity of the loaded granular cargo are obtained; Substitute the current real-time particle size and the real-time humidity into the gate trigger threshold calculation formula to obtain the current gate trigger threshold; the gate trigger threshold calculation formula is as follows:

[0006] Among them, the basic gate triggering threshold is a preset fixed value. and are weight parameters, is the humidity deviation coefficient calculated based on the current real-time humidity and the preset reference humidity, is a particle size deviation coefficient calculated based on the current real-time particle size and a preset reference particle size; Re-acquire the real-time loading weight, calculate the target difference, and determine whether the current target difference is less than or equal to the current gate triggering threshold; If the current target difference is greater than the current gate triggering threshold, jump to the step of obtaining the real-time particle size and real-time humidity of the granular cargo being loaded; If the current target difference is less than or equal to the current gate closing trigger threshold, the gate is closed.

[0007] Optionally, after closing the gate, the method for controlling the loading weight of the granular cargo of the present invention further includes: Obtaining the actual loading weight of the vehicle, the target real-time granularity corresponding to when the gate is closed, the target real-time humidity, and the target gate closing trigger threshold; Based on the linear model and the online learning algorithm, the actual loading weight, the target real-time granularity, the target real-time humidity and the target gate triggering threshold are updated. and stated .

[0008] Optionally, the linear model is defined as:

[0009] in, , is the loading error; Based on the linear model and the online learning algorithm, the actual loading weight, the target real-time granularity, the target real-time humidity and the target gate triggering threshold are updated. and stated , specifically including: According to the target real-time granularity, calculate ; According to the target real-time humidity, calculate the target ; Calculate the target vehicle load according to the actual vehicle load, the target vehicle load and the target gate trigger threshold. ; Based on the stochastic gradient descent algorithm, according to the , and stated Update the and stated .

[0010] Optionally, based on the stochastic gradient descent algorithm, , and stated Update the and stated , specifically including: The , and stated Substitute into the following formula to get the updated and stated :

[0011] in, is the learning rate, Equal to the opposite of the loading error.

[0012] Optionally, based on the stochastic gradient descent algorithm, , and stated Update the and stated , specifically including: The , and stated Substitute into the following formula to get the updated and stated :

[0013] in, is the regularization coefficient.

[0014] Optionally, according to the target real-time granularity, calculate , specifically including: Substituting the target real-time granularity and the preset reference granularity into the following formula, we can obtain :

[0015] in, is the real-time granularity, is the preset reference granularity; According to the target real-time humidity, calculate the target , specifically including: Substitute the target real-time humidity and the preset reference humidity into the following formula to obtain :

[0016] in, is the real-time humidity, The preset reference humidity; Calculate the target vehicle load according to the actual vehicle load, the target vehicle load and the target gate trigger threshold. , specifically including: Subtract the target loading weight from the actual loading weight to obtain the target loading error. ; The target gate trigger threshold and the Substitute into the following formula to obtain : .

[0017] Optionally, before obtaining basic information of the vehicle, the method for controlling the loading weight of the granular cargo of the present invention further includes: Acquire historical loading data, the historical loading data including a plurality of sample data, the sample data including a sample gate closing trigger threshold when the gate is closed, a carriage position, a carriage gross weight, a carriage tare weight, a vehicle identification, a sample target loading weight, a sample loading error, a sample particle size of the loaded granular cargo, and a sample humidity; Performing data preprocessing on the historical loading data; the data preprocessing includes missing value processing, outlier processing and data normalization processing; Based on a preset correlation analysis method, the correlation coefficient between each sample feature and the gate triggering threshold is calculated according to the historical loading data after data preprocessing; the sample features include carriage position, carriage gross weight, carriage tare weight, vehicle identification, target loading weight, loading error, granularity and humidity; Selecting a first sample feature whose correlation coefficient is greater than a preset coefficient threshold; Based on a recursive feature elimination algorithm, screening second sample features from the first sample features; The second sample feature is defined as the sample feature used in this application.

[0018] In a second aspect, the present invention further provides a device for controlling the loading weight of a granular cargo, which is applied to the method for controlling the loading weight of a granular cargo as described above, and the device for controlling the loading weight of a granular cargo comprises: A first acquisition module, used to acquire basic information of the vehicle, wherein the basic information includes a target loading weight; A second acquisition module is used to acquire the real-time loading weight of the vehicle after the vehicle compartment is placed on a track scale as a whole; A calculation module, used for calculating a target difference between the real-time loading weight and the target loading weight; A first judgment module is used to judge whether the target difference is less than a preset difference threshold; A first jump module, configured to jump to the step of obtaining the real-time loading weight of the vehicle if the target difference is not less than a preset difference threshold; A third acquisition module is used to acquire the real-time particle size and real-time humidity of the granular cargo being loaded if the target difference is less than a preset difference threshold; The substitution module is used to substitute the current real-time particle size and the real-time humidity into the gate trigger threshold calculation formula to obtain the current gate trigger threshold; the gate trigger threshold calculation formula is as follows:

[0019] Among them, the basic gate triggering threshold is a preset fixed value. and are weight parameters, is the humidity deviation coefficient calculated based on the current real-time humidity and the preset reference humidity, is a particle size deviation coefficient calculated based on the current real-time particle size and a preset reference particle size; A second judgment module is used to re-acquire the real-time loading weight, calculate the target difference, and judge whether the current target difference is less than or equal to the current gate triggering threshold; A second jump module, configured to jump to the step of obtaining the real-time particle size and real-time humidity of the granular cargo being loaded if the current target difference is greater than the current gate triggering threshold; The closing module is used to close the gate if the current target difference is less than or equal to the current gate closing trigger threshold.

[0020] In a third aspect, the present invention further provides a device for controlling the loading weight of a granular cargo, comprising: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the method for controlling the loading weight of the particulate cargo as described above.

[0021] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for controlling the loading weight of the granular cargo as described above is implemented.

[0022] The present invention adopts the above technical solution. In the first stage, that is, the target difference between the real-time loading weight and the target loading weight is not less than the preset difference threshold, the target difference between the real-time loading weight and the target loading weight will be continuously monitored. When the target difference is less than the preset difference threshold, the second stage is entered. In the second stage, the real-time particle size and real-time humidity of the loaded granular goods will be continuously obtained, the gate trigger threshold will be calculated, and it will be determined whether the current target difference is less than or equal to the current gate trigger threshold. If so, the gate will be closed, otherwise, the new gate trigger threshold and target difference will continue to be calculated and compared until it is determined that the current target difference is less than or equal to the current gate trigger threshold. In this way, by dynamically adjusting the gate trigger threshold according to the real-time particle size and real-time humidity of the loaded granular goods, the present invention does not need a quantitative feeder and a quantitative bin, and improves the control accuracy of the granular cargo loading weight under existing restricted conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 This is a schematic diagram of an application scenario of a method for controlling the loading weight of granular cargo provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of the control principle of a method for controlling the loading weight of granular cargo provided by an embodiment of the present invention; Figure 3 It is a flow chart of a method for controlling the loading weight of granular cargo provided by an embodiment of the present invention; Figure 4 It is a structural schematic diagram of a device for controlling the loading weight of granular cargo provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of the structure of a device for controlling the loading weight of granular cargo provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0026] Figure 1 It is a schematic diagram of an application scenario of a method for controlling the loading weight of granular cargo provided in an embodiment of the present invention. Figure 2 Schematic diagram of the control principle of a method for controlling the loading weight of granular cargo provided by an embodiment of the present invention. Figure 1 and Figure 2 The overall control logic of the present invention includes third-party equipment, a sensor layer, a data processing layer and a control layer. The third-party equipment includes a carriage position detection device, a track scale and a vehicle identity recognition device; the sensor layer includes a moisture sensor and an image sensor, the moisture sensor is installed on the inner wall of the buffer bin of the feeder, and the image sensor is installed just above the carriage, and the image sensor can be a visible light camera; the data processing layer includes a data processing calculation device and an image processing calculation device, and the control layer includes a gate.

[0027] In the actual loading process, the gate of the feeder is opened, and the granular cargo in the feeder will flow into the carriage. When loading begins, the gate opening can be adjusted to 100% to improve loading efficiency. During the entire loading process, the vehicle travels in the driving direction, and the carriage position detection device continuously obtains the carriage position information and sends it to the data processing and calculation device. After the data processing and calculation device determines that the carriage is on the track scale as a whole according to the carriage position information, it confirms that it has entered the first stage of the tail precision feeding stage. At this time, the data processing and calculation device sends an opening adjustment instruction to the gate opening control device (not shown in the figure), and the gate opening control device adjusts the gate opening according to the opening adjustment instruction. The opening adjustment instruction is used to adjust the gate opening from 100% to 30% or other openings less than 100% to slow down the material dropping speed and improve the accuracy of controlling the amount of material dropping.

[0028] In the first stage, the data processing and computing device obtains the vehicle identity through the vehicle identity recognition device. The vehicle identity can be a vehicle code or a license plate number. The data processing and computing device queries the preset database according to the vehicle identity to obtain the basic information of the vehicle. The basic information can include the target loading weight and the tare weight of the carriage. The data processing and computing device also obtains the gross weight of the carriage through the track scale, and subtracts the tare weight of the carriage from the gross weight of the carriage to obtain the real-time loading weight. After each acquisition of the real-time loading weight, the data processing and computing device will calculate the target difference between the real-time loading weight and the target loading weight. If the target difference is not less than the preset difference threshold, the real-time loading weight will continue to be acquired. If the target difference is less than the preset difference threshold, the second stage of the tail precision feeding stage will be entered.

[0029] In the second stage, the data processing and computing device obtains the humidity information of the loaded granular cargo (i.e., the granular cargo in the buffer bin) through the moisture sensor, and calculates the real-time humidity of the loaded granular cargo in percentage (%). The image processing and computing device obtains the image information of the loaded granular cargo through the image sensor, calculates the real-time particle size of the loaded granular cargo in millimeters (mm), and sends the real-time particle size to the data processing and computing device, which can be the average diameter of each granular cargo in the image.

[0030] The data processing and calculation device will continuously obtain the real-time particle size and real-time humidity of the loaded granular cargo, and calculate the corresponding gate trigger threshold. After calculating the gate trigger threshold each time, the data processing and calculation device will determine whether the current target difference is less than or equal to the current gate trigger threshold. If so, it will send a gate closing instruction to the gate opening control device. The gate opening control device will close the gate according to the gate closing instruction and feedback the opening adjustment result data to the data processing and calculation device; if the current target difference is greater than the current gate trigger threshold, the new gate trigger threshold and target difference will continue to be calculated and compared until it is determined that the current target difference is less than or equal to the current gate trigger threshold.

[0031] The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings.

[0032] Figure 3 FIG. 1 is a flow chart of a method for controlling the loading weight of granular cargo provided by an embodiment of the present invention. Figure 3 As shown, this process includes: Step 301: Obtain basic information of the vehicle, including the target loading weight.

[0033] Specifically, the basic information of each vehicle is stored in a preset database. In actual application, the basic information of the vehicle can be obtained by obtaining the vehicle identity and querying the database according to the vehicle identity. The basic information may also include the tare weight of the vehicle compartment.

[0034] Step 302: After the vehicle compartment is placed on the track scale as a whole, the real-time loading weight of the vehicle is obtained.

[0035] It should be noted that the method for obtaining the real-time loading weight can be found in the aforementioned related content and will not be repeated here.

[0036] Step 303: Calculate the target difference between the real-time loading weight and the target loading weight.

[0037] Step 304: Determine whether the target difference is less than a preset difference threshold; if the target difference is not less than the preset difference threshold, jump to the step of obtaining the real-time loading weight of the vehicle; if the target difference is less than the preset difference threshold, execute step 305.

[0038] Among them, the preset difference threshold can be equal to 2 tons.

[0039] Step 305: Obtain the real-time particle size and real-time humidity of the granular cargo being loaded.

[0040] It should be noted that the method for obtaining the real-time particle size and real-time humidity can refer to the aforementioned related content and will not be repeated here.

[0041] Step 306: Substitute the current real-time particle size and real-time humidity into the gate trigger threshold calculation formula to obtain the current gate trigger threshold in kg; the gate trigger threshold calculation formula is as follows: ...... (1) The basic gate triggering threshold is a preset fixed value. For example, the basic gate triggering threshold is equal to 650. and are weight parameters, is the humidity deviation coefficient calculated based on the current real-time humidity and the preset reference humidity. It is the particle size deviation coefficient calculated based on the current real-time particle size and the preset reference particle size.

[0042] Step 307: reacquire the real-time loading weight, calculate the target difference, and determine whether the current target difference is less than or equal to the current gate triggering threshold; if the current target difference is greater than the current gate triggering threshold, jump to the step of acquiring the real-time particle size and real-time humidity of the loaded granular cargo; if the current target difference is less than or equal to the current gate triggering threshold, execute step 308.

[0043] Specifically, it is necessary to obtain the real-time loading weight of the vehicle again, calculate the target difference between the real-time loading weight and the target loading weight, and obtain the current target difference. Then, determine whether the current target difference is less than or equal to the current gate triggering threshold. If the current target difference is greater than the current gate triggering threshold, jump to the step of obtaining the real-time particle size and real-time humidity of the loaded granular cargo; if the current target difference is less than or equal to the current gate triggering threshold, execute step 308.

[0044] Step 308: Close the gate.

[0045] Specifically, the gate may be a hydraulic gate. For the specific implementation process of closing the gate, please refer to the aforementioned related content and will not be repeated here.

[0046] The embodiment of the present invention adopts the above technical solution. In the first stage, that is, the stage where the target difference between the real-time loading weight and the target loading weight is not less than the preset difference threshold, the target difference between the real-time loading weight and the target loading weight will be continuously monitored. When it is monitored that the target difference is less than the preset difference threshold, the second stage is entered. In the second stage, the real-time particle size and real-time humidity of the loaded granular goods will be continuously obtained, the gate trigger threshold will be calculated, and it will be determined whether the current target difference is less than or equal to the current gate trigger threshold. If so, the gate will be closed, otherwise, the new gate trigger threshold and target difference will continue to be calculated and compared until it is determined that the current target difference is less than or equal to the current gate trigger threshold. In this way, by dynamically adjusting the gate trigger threshold according to the real-time particle size and real-time humidity of the loaded granular goods, the present invention does not need a quantitative feeder and a quantitative bin, and improves the control accuracy of the granular goods loading weight under existing restricted conditions.

[0047] In the embodiment of the present invention, after closing the gate, the method for controlling the loading weight of the granular cargo of the present invention may further include: (1) Obtain the actual loading weight of the vehicle, the target real-time granularity corresponding to the gate closing, the target real-time humidity, and the target gate closing trigger threshold.

[0048] (2) Based on the linear model and online learning algorithm, the target real-time granularity, target real-time humidity and target gate trigger threshold are updated. and .

[0049] This can improve and The accuracy of the weight control of the granular cargo loading in the next carriage can be improved.

[0050] In the embodiment of the present invention, the linear model is defined as: ...... (2) in, , Loading error.

[0051] Based on the linear model and online learning algorithm, the system updates the actual loading weight, target real-time granularity, target real-time humidity and target gate trigger threshold. and , which may include: (1) Calculate according to the target real-time granularity .

[0052] In the embodiment of the present invention, according to the target real-time granularity, the calculation , which may include: Substitute the target real-time granularity and the preset reference granularity into the following formula to obtain : ...... (3) in, For real-time granularity, The preset base granularity.

[0053] (2) Calculate the target based on the target real-time humidity .

[0054] In the embodiment of the present invention, the target real-time humidity is calculated. , which may include: Substitute the target real-time humidity and the preset reference humidity into the following formula to obtain : ...... (4) in, For real-time humidity, The preset reference humidity.

[0055] (3) Calculate the actual loading weight, target loading weight and target gate trigger threshold. .

[0056] In the embodiment of the present invention, the actual loading weight, the target loading weight and the target gate triggering threshold are calculated. , which may include: (3.1) Subtract the target loading weight from the actual loading weight to get the target loading error .

[0057] (3.2) Set the target gate trigger threshold and Substituting into the following formula, we get : ...... (5) (4) Based on the stochastic gradient descent algorithm, , and renew and .

[0058] In the embodiment of the present invention, based on the stochastic gradient descent algorithm, , and renew and , which may include: Will , and Substitute the following formula to get the updated and : ...... (6) in, is the learning rate, Equal to the opposite of the loading error.

[0059] In the embodiment of the present invention, based on the stochastic gradient descent algorithm, , and renew and , specifically, it may also include: Will , and Substitute the following formula to get the updated and : ...... (7) in, is the regularization coefficient.

[0060] In this way, by introducing the L2 regularization term, it is possible to prevent parameter overfitting or excessive fluctuation, which is beneficial to further improve the accuracy of the control result of the present invention.

[0061] In the embodiment of the present invention, before obtaining the basic information of the vehicle, the method for controlling the loading weight of the granular cargo of the present invention may further include: (1) Obtain historical loading data. The historical loading data includes multiple sample data. One sample data includes the sample gate closing trigger threshold when the gate is closed, the carriage position, the carriage gross weight, the carriage tare weight, the vehicle identification, the sample target loading weight, the sample loading error, the sample particle size of the loaded granular cargo, and the sample humidity.

[0062] It should be noted that in order to ensure the quality and diversity of the data, long-term data collection can be carried out under different operating conditions, such as different weather and different coal sources.

[0063] (2) Perform data preprocessing on historical loading data; data preprocessing includes missing value processing, outlier processing and data normalization processing.

[0064] Specifically, when processing missing values, for humidity and particle size data, if missing values ​​occur, linear interpolation can be used to fill them; for loading error data, if the missing values ​​are small, the corresponding sample data can be deleted; if the missing values ​​are large, the mean or median can be used to fill them.

[0065] When dealing with outliers, use statistical methods, such as the Z-score method, to detect outliers in the data. Correct or delete humidity, particle size, and loading error data that are outside the normal range. For example, if a humidity exceeds 100%, it is determined to be an outlier and the humidity can be modified or the sample data containing the humidity can be deleted.

[0066] During data normalization, numerical data such as sample particle size and sample humidity in historical loading data are normalized and scaled to the interval [0, 1] to eliminate the dimensional influence between different features. The present invention can specifically use the Min-Max normalization method, and the corresponding formula is: ...... (8) in, is the normalized value; is the original value; is the minimum value of the feature; is the maximum value of the feature.

[0067] (3) Based on the preset correlation analysis method, the correlation coefficient between each sample feature and the gate triggering threshold is calculated according to the historical loading data after data preprocessing; the sample features include carriage position, carriage gross weight, carriage tare weight, vehicle identification, target loading weight, loading error, particle size and humidity.

[0068] Specifically, the preset correlation analysis method can be the Pearson correlation coefficient method of the prior art. In a specific example, assuming that the historical loading data includes 100 sample data, there will be 100 sample granularities and sample gate trigger thresholds corresponding to each sample granularity. Substitute the 100 sample granularities and the sample gate trigger thresholds corresponding to each sample granularity into the calculation formula of the Pearson correlation coefficient to obtain the correlation coefficient between the granularity and the gate trigger threshold. In the same way, the correlation coefficients between other sample features and the gate trigger thresholds can be calculated, which will not be repeated here.

[0069] (4) Select the first sample feature whose correlation coefficient is greater than a preset coefficient threshold.

[0070] (5) Based on the recursive feature elimination algorithm, the second sample features are further screened from the first sample features, which is beneficial to improving the control efficiency and accuracy of the present invention.

[0071] (6) Define the second sample feature as the sample feature used in this application.

[0072] It should be noted that, in the present invention, the second sample characteristics include particle size and humidity. Also, the particle cargo may be coal or ore.

[0073] Based on a general inventive concept, the present invention also provides a device for controlling the loading weight of granular cargo. Figure 4 Schematic diagram of a device for controlling the loading weight of granular cargo provided by an embodiment of the present invention. Figure 4 As shown, the device comprises: The first acquisition module 41 is used to acquire basic information of the vehicle, where the basic information includes a target loading weight.

[0074] The second acquisition module 42 is used to acquire the real-time loading weight of the vehicle after the vehicle compartment is placed on the track scale as a whole.

[0075] The calculation module 43 is used to calculate the target difference between the real-time loading weight and the target loading weight.

[0076] The first judgment module 44 is used to judge whether the target difference is less than a preset difference threshold.

[0077] The first jump module 45 is used to jump to the step of obtaining the real-time loading weight of the vehicle if the target difference is not less than a preset difference threshold.

[0078] The third acquisition module 46 is used to acquire the real-time particle size and real-time humidity of the granular cargo being loaded if the target difference is less than a preset difference threshold.

[0079] The substitution module 47 is used to substitute the current real-time particle size and real-time humidity into the gate trigger threshold calculation formula to obtain the current gate trigger threshold; the gate trigger threshold calculation formula is as follows:

[0080] Among them, the basic gate triggering threshold is a preset fixed value. and are weight parameters, is the humidity deviation coefficient calculated based on the current real-time humidity and the preset reference humidity. It is the particle size deviation coefficient calculated based on the current real-time particle size and the preset reference particle size.

[0081] The second judgment module 48 is used to re-acquire the real-time loading weight, calculate the target difference, and judge whether the current target difference is less than or equal to the current gate triggering threshold.

[0082] The second jump module 49 is used to jump to the step of obtaining the real-time particle size and real-time humidity of the granular cargo being loaded if the current target difference is greater than the current gate triggering threshold.

[0083] The closing module 410 is configured to close the gate if the current target difference is less than or equal to the current gate closing triggering threshold.

[0084] Optionally, the device for controlling the loading weight of granular cargo of the present invention may further include: The fourth acquisition module is used to obtain the actual loading weight of the vehicle, the target real-time granularity corresponding to the gate closing, the target real-time humidity and the target gate closing trigger threshold.

[0085] The parameter update module is used to update the actual loading weight, target real-time granularity, target real-time humidity and target gate trigger threshold based on the linear model and online learning algorithm. and .

[0086] Optionally, a linear model is defined as:

[0087] in, , Loading error.

[0088] The parameter update module may specifically include: The first calculation unit is used to calculate according to the target real-time granularity .

[0089] The second calculation unit is used to calculate the target according to the target real-time humidity. .

[0090] The third calculation unit is used to calculate the actual loading weight, the target loading weight and the target gate triggering threshold. .

[0091] Parameter update unit, used based on stochastic gradient descent algorithm, according to , and renew and .

[0092] Optionally, the parameter updating unit can be used to: Will , and Substitute the following formula to get the updated and :

[0093] in, is the learning rate, Equal to the opposite of the loading error.

[0094] Optionally, the parameter updating unit may also be used for: Will , and Substitute the following formula to get the updated and :

[0095] in, is the regularization coefficient.

[0096] Optionally, the first computing unit may be specifically configured to: Substitute the target real-time granularity and the preset reference granularity into the following formula to obtain :

[0097] in, For real-time granularity, The preset base granularity.

[0098] The second computing unit may be specifically used for: Substitute the target real-time humidity and the preset reference humidity into the following formula to obtain :

[0099] in, For real-time humidity, The preset reference humidity.

[0100] The third computing unit may be specifically used for: Subtract the target loading weight from the actual loading weight to get the target loading error ; Set the target gate trigger threshold and Substituting into the following formula, we get : .

[0101] Optionally, the device for controlling the loading weight of granular cargo of the present invention may further include: a feature screening module for: (1) Obtain historical loading data. The historical loading data includes multiple sample data, including the sample gate closing trigger threshold when the gate is closed, the carriage position, the carriage gross weight, the carriage tare weight, the vehicle identification, the sample target loading weight, the sample loading error, the sample particle size of the loaded granular cargo, and the sample humidity.

[0102] (2) Perform data preprocessing on historical loading data; data preprocessing includes missing value processing, outlier processing and data normalization processing.

[0103] (3) Based on the preset correlation analysis method, the correlation coefficient between each sample feature and the gate triggering threshold is calculated according to the historical loading data after data preprocessing; the sample features include carriage position, carriage gross weight, carriage tare weight, vehicle identification, target loading weight, loading error, particle size and humidity.

[0104] (4) Select the first sample feature whose correlation coefficient is greater than a preset coefficient threshold.

[0105] (5) Based on the recursive feature elimination algorithm, the second sample features are screened from the first sample features.

[0106] (6) Define the second sample feature as the sample feature used in this application.

[0107] Based on a general inventive concept, the present invention also provides a device for controlling the loading weight of granular cargo. Figure 5 Schematic diagram of a device for controlling the loading weight of granular cargo provided by an embodiment of the present invention. Figure 5 As shown, the device 500 includes: at least one processor 510; and, A memory 530 is communicatively connected to at least one processor 510; wherein, The memory 530 stores instructions 520 that can be executed by at least one processor 510. The instructions 520 are executed by the at least one processor 510 so that the at least one processor 510 can implement the method for controlling the loading weight of the particulate cargo as described above.

[0108] Based on a general inventive concept, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for controlling the loading weight of the granular cargo as described above is implemented.

[0109] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0110] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0111] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0112] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0113] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0114] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0115] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0116] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0117] 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. A method for controlling the loading weight of granular cargo, characterized in that: include: Obtaining basic information of the vehicle, wherein the basic information includes a target loading weight; After the vehicle compartment is placed on a track scale as a whole, obtaining the real-time loading weight of the vehicle; Calculating a target difference between the real-time loading weight and the target loading weight; Determine whether the target difference is less than a preset difference threshold; If the target difference is not less than the preset difference threshold, jump to the step of obtaining the real-time loading weight of the vehicle; If the target difference is less than the preset difference threshold, the real-time particle size and real-time humidity of the loaded granular cargo are obtained; Substitute the current real-time particle size and the real-time humidity into the gate trigger threshold calculation formula to obtain the current gate trigger threshold; the gate trigger threshold calculation formula is as follows: Among them, the basic gate triggering threshold is a preset fixed value. and are weight parameters, is the humidity deviation coefficient calculated based on the current real-time humidity and the preset reference humidity, is a particle size deviation coefficient calculated based on the current real-time particle size and a preset reference particle size; Re-acquire the real-time loading weight, calculate the target difference, and determine whether the current target difference is less than or equal to the current gate triggering threshold; If the current target difference is greater than the current gate triggering threshold, jump to the step of obtaining the real-time particle size and real-time humidity of the granular cargo being loaded; If the current target difference is less than or equal to the current gate closing trigger threshold, the gate is closed.

2. The method for controlling the loading weight of granular cargo according to claim 1, characterized in that: After closing the gate, the method further comprises: Obtaining the actual loading weight of the vehicle, the target real-time granularity corresponding to when the gate is closed, the target real-time humidity, and the target gate closing trigger threshold; Based on the linear model and the online learning algorithm, the actual loading weight, the target real-time granularity, the target real-time humidity and the target gate triggering threshold are updated. and stated .

3. The method for controlling the loading weight of granular cargo according to claim 2, characterized in that: The linear model is defined as: in, , is the loading error; Based on the linear model and the online learning algorithm, the actual loading weight, the target real-time granularity, the target real-time humidity and the target gate triggering threshold are updated. and stated , specifically including: According to the target real-time granularity, calculate ; According to the target real-time humidity, calculate the target ; Calculate the target vehicle load according to the actual vehicle load, the target vehicle load and the target gate trigger threshold. ; Based on the stochastic gradient descent algorithm, according to the , and stated Update the and stated .

4. The method for controlling the loading weight of granular cargo according to claim 3, characterized in that: Based on the stochastic gradient descent algorithm, according to the , and stated Update the and stated , specifically including: The , and stated Substitute into the following formula to get the updated and stated : in, is the learning rate, Equal to the opposite of the loading error.

5. The method for controlling the loading weight of granular cargo according to claim 3, characterized in that: Based on the stochastic gradient descent algorithm, according to the , and stated Update the and stated , specifically including: The , and stated Substitute into the following formula to get the updated and stated : in, is the regularization coefficient.

6. The method for controlling the loading weight of granular cargo according to claim 3, characterized in that: According to the target real-time granularity, calculate , specifically including: Substituting the target real-time granularity and the preset reference granularity into the following formula, we can obtain : in, is the real-time granularity, is the preset reference granularity; According to the target real-time humidity, calculate the target , specifically including: Substitute the target real-time humidity and the preset reference humidity into the following formula to obtain : in, is the real-time humidity, The preset reference humidity; Calculate the target vehicle load according to the actual vehicle load, the target vehicle load and the target gate trigger threshold. , specifically including: Subtract the target loading weight from the actual loading weight to obtain the target loading error. ; The target gate trigger threshold and the Substitute into the following formula to obtain : 。 7. The method for controlling the loading weight of granular cargo according to claim 1, characterized in that: Before obtaining the basic information of the vehicle, it also includes: Acquire historical loading data, the historical loading data including a plurality of sample data, the sample data including a sample gate closing trigger threshold when the gate is closed, a carriage position, a carriage gross weight, a carriage tare weight, a vehicle identification, a sample target loading weight, a sample loading error, a sample particle size of the loaded granular cargo, and a sample humidity; Performing data preprocessing on the historical loading data; the data preprocessing includes missing value processing, outlier processing and data normalization processing; Based on a preset correlation analysis method, the correlation coefficient between each sample feature and the gate triggering threshold is calculated according to the historical loading data after data preprocessing; the sample features include carriage position, carriage gross weight, carriage tare weight, vehicle identification, target loading weight, loading error, granularity and humidity; Selecting a first sample feature whose correlation coefficient is greater than a preset coefficient threshold; Based on a recursive feature elimination algorithm, screening second sample features from the first sample features; The second sample feature is defined as the sample feature used in this application.

8. A device for controlling the loading weight of granular cargo, characterized in that: The method for controlling the loading weight of a granular cargo according to any one of claims 1 to 7, wherein the device for controlling the loading weight of the granular cargo comprises: A first acquisition module, used to acquire basic information of the vehicle, wherein the basic information includes a target loading weight; A second acquisition module is used to acquire the real-time loading weight of the vehicle after the vehicle compartment is placed on a track scale as a whole; A calculation module, used for calculating a target difference between the real-time loading weight and the target loading weight; A first judgment module, used to judge whether the target difference is less than a preset difference threshold; A first jump module, configured to jump to the step of obtaining the real-time loading weight of the vehicle if the target difference is not less than a preset difference threshold; A third acquisition module is used to acquire the real-time particle size and real-time humidity of the granular cargo being loaded if the target difference is less than a preset difference threshold; The substitution module is used to substitute the current real-time particle size and the real-time humidity into the gate trigger threshold calculation formula to obtain the current gate trigger threshold; the gate trigger threshold calculation formula is as follows: Among them, the basic gate triggering threshold is a preset fixed value. and are weight parameters, is the humidity deviation coefficient calculated based on the current real-time humidity and the preset reference humidity, is a particle size deviation coefficient calculated based on the current real-time particle size and a preset reference particle size; A second judgment module is used to re-acquire the real-time loading weight, calculate the target difference, and judge whether the current target difference is less than or equal to the current gate triggering threshold; A second jump module, configured to jump to the step of obtaining the real-time particle size and real-time humidity of the granular cargo being loaded if the current target difference is greater than the current gate triggering threshold; The closing module is used to close the gate if the current target difference is less than or equal to the current gate closing trigger threshold.

9. A device for controlling the loading weight of granular cargo, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the method for controlling the loading weight of particulate cargo according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for controlling the loading weight of particulate cargo according to any one of claims 1 to 7 is implemented.

Images