A method for measuring flow rate of multi-metallic nodule in wide temperature range

Abstract

The present application relates to the technical field of deep-sea mining, and discloses a wide-temperature-range multi-metal nodule conveying flow measurement method. Coil temperature, ore temperature, sensor voltage data and ore flow detection data are collected based on triple circulation for metal nodule flow detection, a characteristic variable and a correction model are constructed based on the Bloch law, a training set and a verification set are obtained according to the characteristic variable, the correction model and the detection data, and the correction model is trained based on the training set and the verification set. Coil temperature and ore temperature of a detection coil in an actual mining process and voltage data of a sensor are obtained and input into the correction model, corresponding ore flow is obtained, and measurement of multi-metal nodule conveying flow is completed. The problem that existing deep-sea mining cannot accurately measure multi-metal nodule ore flow in a wide temperature change range is solved.

Description

Technical Field

[0001] This invention relates to the field of deep-sea mining technology, and in particular to a method for measuring the transport flow rate of polymetallic nodules over a wide temperature range. Background Technology

[0002] In deep-sea mining, polymetallic nodules are collected by mining vehicles and transported to surface support platforms via lifting pipelines. To assess mining efficiency and dynamically adjust the mining vehicle's trajectory, it is necessary to measure the amount of nodules passing through the pipeline per unit time (also known as flow rate) in real time, thus forming closed-loop feedback data. The polymetallic nodule flow rate sensor consists of a detection coil and a processing circuit. When the nodule passes through the pipeline encircled by the detection coil, it causes a change in magnetic resistance. This change is processed into a voltage signal by the sensor's processing circuit. The deep-sea mining control system uses the voltage signal value, according to a mathematical expression provided by the sensor, to determine the magnitude of the polymetallic nodule flow rate.

[0003] The measurement principle described above is based on the assumption that changes in magnetic reluctance are solely due to the amount of polymetallic nodules passing through the pipe per unit time, without considering other factors. The shortcoming of this assumption is that it fails to account for the fact that the magnetic reluctance of the magnetic material is related to temperature changes. Changes in the magnetic reluctance of the coil itself and the polymetallic nodules with temperature can be processed by the sensor's processing circuitry into voltage signals, generating false flow data and causing measurement errors. This, in turn, affects the decision-making of the deep-sea mining control system. Summary of the Invention

[0004] This invention provides a method for measuring the flow rate of polymetallic nodules over a wide temperature range, in order to solve the problem that existing deep-sea mining methods cannot accurately measure the flow rate of polymetallic nodule ore over a wide temperature variation range.

[0005] To achieve the above objectives, the present invention employs the following technical solution:

[0006] In a first aspect, the present invention provides a method for measuring the transport flow rate of polymetallic nodules over a wide temperature range, comprising the following steps:

[0007] Step 1: Based on triple-loop acquisition of coil temperature, ore temperature, sensor voltage data and ore flow detection data for metal nodule flow detection, construct feature variables and calibration model based on Bloch's law, and obtain training set and validation set based on feature variables, calibration model and detection data, and train calibration model based on training set and validation set.

[0008] Step 2: Obtain the coil temperature of the detection coil, the ore temperature, and the voltage data of the sensor during the actual mining process, and input them into the calibration model to obtain the corresponding ore flow rate, thus completing the measurement of the polymetallic nodule transport flow rate.

[0009] Furthermore, the method of acquiring detection data on coil temperature, ore temperature, sensor voltage, and ore flow rate for metal nodule flow detection based on triple-loop acquisition includes: setting corresponding initial values ​​for coil temperature, ore temperature, and ore flow rate; constructing a nested loop process based on the initial values; executing the nested loop process; and recording the data on coil temperature, ore temperature, ore flow rate, and sensor voltage in all loops as detection data.

[0010] Furthermore, the process of constructing a nested loop based on the initial loop value includes: calculating the number of cycles for the coil temperature cycle, the ore temperature cycle, and the ore flow rate cycle based on the initial loop value, and constructing a nested loop based on the number of cycles.

[0011] Through the above operations, the detection data based on triple-loop acquisition comprehensively covers all data combinations, which can more intuitively reflect the structural relationship of the data. Furthermore, the parameters and conditions of each loop dimension can be independently controlled, which can more effectively generate a dedicated dataset for wide-temperature detection of ore flow.

[0012] Furthermore, the initial values ​​of the cycle include: initial coil temperature, final coil temperature, coil temperature increment step, initial ore temperature, final ore temperature, increment step of ore temperature, initial ore flow rate, final ore flow rate, and increment step of ore flow rate.

[0013] The number of cycles for the coil temperature cycle is calculated using the following formula:

[0014] ;

[0015] in, This indicates the number of cycles in the coil temperature cycle. Indicates the coil termination temperature. Indicates the initial temperature of the coil. This indicates the step size for increasing the coil temperature;

[0016] The number of cycles for the ore temperature cycling is calculated using the following formula:

[0017] ;

[0018] in, This indicates the number of cycles in the ore temperature cycle. Indicates the ore termination temperature. Indicates the initial temperature of the ore. Indicates the step size for increasing the temperature of the ore;

[0019] The number of cycles for the ore flow circulation is calculated using the following formula:

[0020] ;

[0021] in, This indicates the number of cycles in the ore flow circulation. Indicates the final flow rate of the ore. Indicates the initial flow rate of the ore. This indicates the increment step of ore flow rate.

[0022] Furthermore, the nested loop construction process is executed in accordance with the loop rules, following the sequence of ore flow circulation, coil temperature circulation, and ore temperature circulation.

[0023] The cyclic rules include: performing one coil temperature cycle for every k ore temperature cycles, performing one ore flow rate cycle for every n coil temperature cycles, and performing a total of m ore flow rate cycles. Each time the ore temperature cycle, coil temperature cycle, and ore flow rate cycle are performed, the coil temperature, ore temperature, and ore flow rate are adjusted according to the corresponding coil temperature growth step, ore temperature growth step, and ore flow rate growth step, respectively.

[0024] After performing one coil temperature cycle, the current ore temperature is adjusted to the initial ore temperature. After performing one ore flow cycle, the current coil temperature is adjusted to the initial coil temperature, and the current ore temperature is adjusted to the initial ore temperature.

[0025] Furthermore, the construction of the characteristic variables and correction model based on Bloch's law includes: constructing the characteristic variables and correction model based on the linear relationship between magnetoresistance and temperature to the 1.5th power in Bloch's law, the common nonlinear influence of coil temperature and ore temperature on the sensor's measurement output, the linear relationship between magnetoresistance and flow rate, and the linear relationship with the square of the sensor's output voltage.

[0026] The temperature Bloch law describes the relationship between magnetic reluctance and temperature in magnetic materials. Choosing a linear relationship of 1.5 times the power of magnetic reluctance and temperature is consistent with the low to medium temperature range of deep-sea mining. Through the above operation, this nonlinear change can be better fitted. Compared with a simple linear term, it can more accurately reflect the influence of temperature on ore flow when the temperature change is large.

[0027] The characteristic variables are expressed by the following formula:

[0028] ;

[0029] in, Indicates the coil temperature. Indicates the temperature of the ore. Indicates common influencing factors. This represents the voltage signal output by the sensor.

[0030] The correction model is expressed by the following formula:

[0031] ;

[0032] in, This represents the ore flow rate output by the calibration model. These are the model coefficients.

[0033] Furthermore, the step of obtaining the training set and validation set based on the feature variables, the calibration model, and the detection data includes: performing combined calculations based on the feature variables, the calibration model, and the detection data to obtain a structured dataset. and For structured datasets and After normalization, the training set and validation set are obtained.

[0034] Furthermore, after normalization to obtain the training and validation sets, the model was trained and corrected using the 5-fold cross-validation method and support vector regression.

[0035] Furthermore, the normalization process is as follows: Standardization methods.

[0036] Furthermore, the calibration model obtains hyperparameters through the GridSearchCV function during training.

[0037] Beneficial effects:

[0038] This invention provides a method for measuring the flow rate of polymetallic nodules over a wide temperature range. It makes significant adjustments to the data usage of the polymetallic nodule flow rate detection sensor, overcoming the problem that the output data of the original device has large errors when the temperature of the ore in the conveying pipeline or the sensor coil itself changes. It can detect the flow rate of polymetallic nodule ore more accurately over a wide temperature range, providing reliable data and an effective detection model for the control system of deep-sea mining. Attached Figure Description

[0039] Figure 1 This is a flowchart of a method for measuring the transport flow rate of polymetallic nodules over a wide temperature range, according to an embodiment of the present invention.

[0040] Figure 2 This is a flowchart of the nested loop process in an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram illustrating the training and use of the calibration model in an embodiment of the present invention. Detailed Implementation

[0042] The technical solution of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Similarly, the terms "an" or "a" and similar terms do not indicate a quantity limitation, but rather indicate the presence of at least one. The terms "connected" or "linked" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up," "down," "left," "right," etc., are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship also changes accordingly.

[0044] Please see Figure 1 This application provides a method for measuring the transport flow rate of polymetallic nodules over a wide temperature range, comprising the following steps:

[0045] Step 1: Based on triple-loop acquisition of coil temperature, ore temperature, sensor voltage data and ore flow detection data for metal nodule flow detection, construct feature variables and calibration model based on Bloch's law, and obtain training set and validation set based on feature variables, calibration model and detection data, and train calibration model based on training set and validation set.

[0046] Please see Figure 2 Specifically, corresponding initial values ​​for coil temperature, ore temperature, and ore flow rate are set. Based on the initial values, a nested loop process is constructed. The nested loop process is executed, and the data of coil temperature, ore temperature, ore flow rate, and sensor voltage in all loops are recorded as detection data.

[0047] The initial values ​​of the cycle include: initial coil temperature, final coil temperature, coil temperature increment step, initial ore temperature, final ore temperature, increment step of ore temperature, initial ore flow rate, final ore flow rate, and increment step of ore flow rate.

[0048] In this embodiment, the initial coil temperature is set to 20°C, the final coil temperature to 40°C, and the coil temperature increment step to 1°C. The initial ore temperature is set to 20°C, the final ore temperature to 60°C, and the ore temperature increment step to 2°C. The initial ore flow rate is set to 600 kg / min, the final ore flow rate to 1200 kg / min, and the ore flow rate increment step to 50 kg / min.

[0049] The number of cycles for coil temperature cycle, ore temperature cycle, and ore flow cycle are calculated based on the initial values ​​of the cycles, and a nested cycle process is constructed based on the number of cycles.

[0050] Among them, the nested loop process is executed in the order of ore flow circulation, coil temperature circulation, and ore temperature circulation, combined with the circulation rules.

[0051] The loop rules include: every k ore temperature loops, the coil temperature loop is executed once; every n coil temperature loops, the ore flow rate loop is executed once; a total of m ore flow rate loops are executed. Each time the ore temperature loop, coil temperature loop, and ore flow rate loop are executed, the coil temperature, ore temperature, and ore flow rate are adjusted according to the corresponding coil temperature increase step, ore temperature increase step, and ore flow rate increase step, respectively.

[0052] After performing one coil temperature cycle, the current ore temperature is adjusted to the initial ore temperature. After performing one ore flow cycle, the current coil temperature is adjusted to the initial coil temperature, and the current ore temperature is adjusted to the initial ore temperature.

[0053] The number of cycles for ore temperature cycling is calculated using the following formula:

[0054] ;

[0055] in, This indicates the number of cycles in the ore temperature cycle. Indicates the ore termination temperature. Indicates the initial temperature of the ore. Indicates the step size for increasing the temperature of the ore;

[0056] The number of coil temperature cycles is calculated using the following formula:

[0057] ;

[0058] in, This indicates the number of cycles in the coil temperature cycle. Indicates the coil termination temperature. Indicates the initial temperature of the coil. This indicates the step size for increasing the coil temperature;

[0059] The number of cycles for ore flow circulation is calculated using the following formula:

[0060] ;

[0061] in, This indicates the number of cycles in the ore flow circulation. Indicates the final flow rate of the ore. Indicates the initial flow rate of the ore. This indicates the increment step of ore flow rate.

[0062] The constructed nested loop process includes:

[0063] Maintain the initial ore flow rate in the conveying pipeline at 600 kg / min and the initial coil temperature at 20°C. Then, set the initial ore temperature to 20°C and perform 20 data acquisition operations. After each data acquisition, adjust the ore temperature according to the ore temperature increase step size until the ore temperature reaches the final ore temperature of 60°C. Throughout this process, maintain the initial ore flow rate at 600 kg / min and the initial coil temperature at 20°C.

[0064] After 20 data acquisitions, the initial coil temperature was adjusted according to the coil temperature increment step, i.e., the coil temperature was adjusted from 20℃ to 21℃, and the ore temperature was adjusted from 60℃ to the initial ore temperature of 20℃. Then, another 20 data acquisitions were performed, and the above process was repeated. That is, for each coil temperature adjustment, the ore temperature was adjusted 20 times until the coil temperature reached the coil termination temperature. Each time, the coil temperature was adjusted according to the coil temperature increment step. During this process, the ore flow rate was maintained at 600 kg / min. A total of 400 continuous data points were collected, including ore temperature, coil temperature, ore flow rate, and voltage signal data output by the sensor.

[0065] After collecting 400 data points, the ore flow rate was adjusted from 600 kg / min to 650 kg / min, the coil temperature was adjusted from 40℃ to 20℃, and the ore temperature was adjusted from 60℃ to 20℃. Then, for each adjustment of the ore flow rate, the coil temperature was adjusted 20 times, and for each adjustment of the coil temperature, the ore temperature was adjusted to 20℃. Thus, a total of 4800 data points were collected (including the previously collected 400 consecutive data points).

[0066] The characteristic variables and correction model constructed based on Bloch's law include: based on the linear relationship between magnetoresistive and temperature to the 1.5th power in Bloch's law, the common nonlinear influence of coil temperature and ore temperature on the sensor's measurement output, the linear relationship between magnetoresistive and flow rate, and the linear relationship with the square of the sensor's output voltage, the characteristic variables and correction model are constructed.

[0067] The characteristic variables are expressed by the following formula:

[0068] ;

[0069] in, Indicates the coil temperature. Indicates the temperature of the ore. Indicates common influencing factors. This represents the voltage signal output by the sensor.

[0070] The calibration model is expressed by the following formula:

[0071] ;

[0072] in, This represents the ore flow rate output by the calibration model. These are the model coefficients.

[0073] Bloch's law describes the relationship between magnetoresistance and temperature in magnetic materials. Choosing a linear relationship of magnetoresistance to the 1.5th power of temperature better fits the low-to-medium temperature range of deep-sea mining, providing a better fit for this non-linear change. Magnetoresistance typically increases with temperature... decline, The Curie temperature is used in polymetallic nodule flow sensors. Since magnetoresistance is proportional to ore flow rate, there is a linear relationship between ore flow rate and the 1.5th power of temperature. Therefore, [the following is a selection criteria]... , As a feature variable, it can better fit this nonlinear change, compared to a simple linear term. and In comparison, it can more accurately reflect the impact of temperature on ore flow, especially when there are large temperature variations.

[0074] Furthermore, coil temperature and ore temperature do not independently affect ore flow rate; they interact. When both change simultaneously, the thermal effects can be superimposed, leading to a more significant change in ore flow rate than when considering either temperature individually. This increases the product term. To capture this coupling effect;

[0075] As for and As a first-order term, since the effect of temperature on ore flow may be nonlinear overall, but the first-order term is the basic part. Adding the first-order term ensures that the model includes temperature effects from simple to complex, avoiding the omission of basic linear contributions. Based on the above, a more accurate calibration model for ore flow detection can be constructed.

[0076] Please see Figure 3 Obtaining training and validation sets based on feature variables, calibration models, and detection data includes: performing combined calculations based on feature variables, calibration models, and detection data to obtain structured datasets. and For structured datasets and After normalization, the training set and validation set are obtained.

[0077] After obtaining the training and validation sets through normalization, the model was further trained and corrected using 5-fold cross-validation and support vector regression. The normalization process was then performed as follows: Standardization methods.

[0078] Specifically, the feature variables are used as the input matrix, and the model output is used as the output matrix. The 4800 collected data points are input sequentially and processed to generate the structured dataset required for training. and The dataset was divided into 4800 data points, and 20 data points were extracted in sequence. 16 data points were extracted as training data and 4 data points were extracted as validation data. After one partition, the dataset was divided into a training set of 3840 data points and a validation set of 960 data points. This partitioning operation was performed 5 times, resulting in a total of 5 training sets and 5 validation sets.

[0079] Data pipeline processing includes data standardization and SVR model specification: First, the scale of the feature data is unified by using the Z-score standardization method to standardize the training data. and The data is converted to a standard normal distribution with a mean of 0 and a standard deviation of 1 to prevent the adverse effects of different data scales on SVR performance. This is achieved by calling the StandardScaler function in Python code. Since the feature input of the calibration model is non-linear, a Gaussian radial basis kernel (RBF) is chosen to map the data to a high-dimensional space, thereby achieving linear regression in the high-dimensional space. A pipeline containing StandardScaler and SVR is created using Pipeline.

[0080] The GridSearchCV function is used to specify hyperparameter search and 5-fold cross-validation. The object constructed using this function is fitted to the training set using the fit function to find the best combination of hyperparameters. Then, the model is retrained on the entire training set using the best parameters to obtain the final calibrated model.

[0081] The optimal hyperparameter combination refers to the set of hyperparameters used in 5-fold cross-validation to calibrate the model. This set of hyperparameters is used in turn for 4 training sessions and 1 validation session, and the accuracy and F1 score are calculated in 5 iterations. The average of these values ​​is then taken, and the set of hyperparameters with the higher average value is considered the optimal hyperparameter combination.

[0082] Step 2: Obtain the coil temperature of the detection coil, the ore temperature, and the voltage data of the sensor during the actual mining process, input them into the calibration model, obtain the corresponding ore flow rate, and complete the measurement of the polymetallic nodule transport flow rate.

[0083] In the actual ore flow measurement process, the temperature TS of the sensor coil, the temperature TM of the polymetallic nodule ore, and the output voltage of the sensor are collected. The data are calculated and processed according to the requirements of the feature input, and the predict function of the calibration model is used to calculate the feature input. The output value of the model is the calculated polymetallic nodule ore flow.

[0084] In the experimental data, under the given standard flow rate of 800 kg / min, when the ore temperature exceeds the initial experimental temperature by 10°C, the flow rate calculated according to the original method of the polymetallic nodule detection sensor deviates by about 14%, showing a large error. However, the flow rate error output by the model of this invention is about 5%. Even when the ore temperature exceeds the initial temperature by 20°C, the maximum deviation between the flow rate data calculated by this invention and the standard flow rate is still within 10%, proving that the method proposed in this invention has significantly improved the stability of the output data over a wider temperature range.

[0085] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A method for measuring the transport flow rate of polymetallic nodules over a wide temperature range, characterized in that, Includes the following steps: Step 1: Based on triple-loop acquisition of coil temperature, ore temperature, sensor voltage data and ore flow detection data for metal nodule flow detection, construct feature variables and calibration model based on Bloch's law, and obtain training set and validation set based on feature variables, calibration model and detection data, and train calibration model based on training set and validation set. The characteristic variable and correction model based on Bloch's law includes: based on the linear relationship between magnetoresistive and temperature to the power of 1.5 in Bloch's law, the common nonlinear influence of coil temperature and ore temperature on the sensor's measurement output, the linear relationship between magnetoresistive and flow rate, and the linear relationship with the square of the sensor's output voltage, the characteristic variable and correction model are constructed. The addition of a product term to the characteristic variables indicates the coupling effect between coil temperature and ore temperature; The characteristic variables are expressed by the following formula: ； in, Indicates the coil temperature. Indicates the temperature of the ore. Indicates common influencing factors. This represents the voltage signal output by the sensor. The correction model is expressed by the following formula: ； in, This represents the ore flow rate output by the calibration model. These are the model coefficients; Step 2: Obtain the coil temperature of the detection coil, the ore temperature, and the voltage data of the sensor during the actual mining process, and input them into the calibration model to obtain the corresponding ore flow rate, thus completing the measurement of the polymetallic nodule transport flow rate.

2. The method for measuring the transport flow rate of polymetallic nodules over a wide temperature range according to claim 1, characterized in that, The method for collecting detection data on coil temperature, ore temperature, sensor voltage, and ore flow rate for metal nodule flow detection based on triple-loop acquisition includes: setting corresponding initial values ​​for coil temperature, ore temperature, and ore flow rate; constructing a nested loop process based on the initial values; executing the nested loop process and recording the data of coil temperature, ore temperature, ore flow rate, and sensor voltage in all loops as detection data.

3. The method for measuring the transport flow rate of polymetallic nodules over a wide temperature range according to claim 2, characterized in that, The process of constructing a nested loop based on the initial loop value includes: calculating the number of cycles for coil temperature cycle, ore temperature cycle, and ore flow rate cycle based on the initial loop value, and constructing a nested loop based on the number of cycles.

4. The method for measuring the transport flow rate of polymetallic nodules over a wide temperature range according to claim 3, characterized in that, The initial values ​​of the cycle include: initial coil temperature, final coil temperature, coil temperature increment step, initial ore temperature, final ore temperature, increment step of ore temperature, initial ore flow rate, final ore flow rate, and increment step of ore flow rate. The number of cycles for the coil temperature cycle is calculated using the following formula: ； in, This indicates the number of cycles in the coil temperature cycle. Indicates the coil termination temperature. Indicates the initial temperature of the coil. This indicates the step size for increasing the coil temperature; The number of cycles for the ore temperature cycling is calculated using the following formula: ； in, This indicates the number of cycles in the ore temperature cycle. Indicates the ore termination temperature. Indicates the initial temperature of the ore. Indicates the step size for increasing the temperature of the ore; The number of cycles for the ore flow circulation is calculated using the following formula: ； in, This indicates the number of cycles in the ore flow circulation. Indicates the final flow rate of the ore. Indicates the initial flow rate of the ore. This indicates the increment step of ore flow rate.

5. The method for measuring the transport flow rate of polymetallic nodules over a wide temperature range according to claim 4, characterized in that, The nested loop construction process is executed in the order of ore flow circulation, coil temperature circulation, and ore temperature circulation, combined with the circulation rules. The cyclic rules include: performing one coil temperature cycle for every k ore temperature cycles, performing one ore flow rate cycle for every n coil temperature cycles, and performing a total of m ore flow rate cycles. Each time the ore temperature cycle, coil temperature cycle, and ore flow rate cycle are performed, the coil temperature, ore temperature, and ore flow rate are adjusted according to the corresponding coil temperature growth step, ore temperature growth step, and ore flow rate growth step, respectively. After performing one coil temperature cycle, the current ore temperature is adjusted to the initial ore temperature. After performing one ore flow cycle, the current coil temperature is adjusted to the initial coil temperature, and the current ore temperature is adjusted to the initial ore temperature.

6. The method for measuring the transport flow rate of polymetallic nodules over a wide temperature range according to claim 1, characterized in that, The step of obtaining the training and validation sets based on feature variables, the calibration model, and the detection data includes: performing combined calculations based on feature variables, the calibration model, and the detection data to obtain a structured dataset. and For structured datasets and After normalization, the training set and validation set are obtained.

7. The method for measuring the transport flow rate of polymetallic nodules over a wide temperature range according to claim 6, characterized in that, After normalization to obtain the training and validation sets, the model was trained and corrected using the 5-fold cross-validation method and support vector regression.

8. The method for measuring the transport flow rate of polymetallic nodules over a wide temperature range according to claim 6, characterized in that, The normalization process is as follows: Standardization methods.

9. The method for measuring the transport flow rate of polymetallic nodules over a wide temperature range according to claim 1, characterized in that, The calibration model obtains hyperparameters through the GridSearchCV function during training.

Images