Coal preparation suspension density detection method and device, storage medium, and computer equipment

Abstract

The present application discloses a method and device for detecting the density of a coal preparation suspension, a storage medium, and a computer device. The method comprises: obtaining a historical pressure difference signal, a historical pressure signal, and a historical density test value of the coal preparation suspension corresponding to a historical sampling moment; determining a pressure difference compensation coefficient, a pressure compensation coefficient, and a target compensation amount corresponding to an initial density detection model based on the historical pressure difference signal, the historical pressure signal, and the historical density test value of the coal preparation suspension; obtaining a coal preparation suspension density detection model based on the pressure difference compensation coefficient, the pressure compensation coefficient, the target compensation amount, and the initial density detection model; obtaining a coal preparation suspension density detection value based on the collected target pressure difference original signal, the target pressure original signal, and the coal preparation suspension density detection model. The present application can detect the density of a coal preparation suspension quickly and accurately in real time while considering multiple influencing factors.

Description

Technical Field

[0001] The present application relates to the field of industrial process technology, and in particular to a method and device for detecting the density of a coal preparation suspension, a storage medium, and a computer device. Background Art

[0002] In coal preparation production, suspension density is a key process parameter in the separation of lump coal, fine coal and coarse coal slime. It is the main factor determining product indicators, washing accuracy and efficiency.

[0003] In the prior art, when determining the density of the coal preparation suspension, a density detection instrument is usually used to determine it. At present, the density detection instruments used in the coal preparation industry can be mainly divided into radioactive source densitometers, ultrasonic densitometers, vibration densitometers, weighing densitometers and differential pressure densitometers according to different measurement principles. The above-mentioned types of density detection instruments are generally based on a single factor, the instrument parameters are fixed, and the comprehensive complexity of the coal preparation density change process is not considered. In addition, the radioactive source densitometer has radiation hazards, the ultrasonic densitometer is very sensitive to bubbles, flow, and vibration in the medium, the measuring tube in the vibration densitometer is severely worn by the suspended particles in the suspension, the executive head of the weighing densitometer requires sufficient installation space and continuous maintenance, and the differential pressure densitometer does not consider the interference of the pressure change caused by the flow of the suspension on the correlation between the pressure difference and the medium density. Therefore, the accuracy of determining the density of the coal preparation suspension by the density detection instrument is low.

[0004] In fact, the density of coal preparation production is affected by the fluctuation of raw coal quality, drift of sorting operation parameters, changes in process disturbances and other uncertain factors, and is always in dynamic fluctuations with frequent changes in operating conditions. Considering only a single factor will inevitably lead to low density detection accuracy. Therefore, how to solve the problem of low detection accuracy and fixed instrument parameters of density meters in the existing technology has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of this, the present application provides a method and device for detecting the density of a coal preparation suspension, a storage medium, and a computer device, which can detect the density of the coal preparation suspension quickly and accurately in real time while taking into account multiple influencing factors.

[0006] According to one aspect of the present application, a method for detecting density of a coal preparation suspension is provided, comprising:

[0007] Obtain the historical differential pressure signal, historical pressure signal and historical density test value of the coal preparation suspension corresponding to the historical sampling time;

[0008] Based on the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension, determine the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount corresponding to the initial density detection model;

[0009] Obtaining a coal preparation suspension density detection model according to the pressure difference compensation coefficient, the pressure compensation coefficient, the target compensation amount and the initial density detection model;

[0010] Based on the collected target pressure difference original signal, target pressure original signal, and the coal preparation suspension density detection model, a coal preparation suspension density detection value is obtained.

[0011] According to another aspect of the present application, a device for detecting density of a coal preparation suspension is provided, comprising:

[0012] An acquisition module is used to acquire a historical pressure difference signal, a historical pressure signal and a historical density test value of the coal preparation suspension corresponding to a historical sampling moment;

[0013] A numerical determination module, for determining a pressure difference compensation coefficient, a pressure compensation coefficient and a target compensation amount corresponding to an initial density detection model based on the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension;

[0014] A model determination module, used for obtaining a coal preparation suspension density detection model according to the pressure difference compensation coefficient, the pressure compensation coefficient, the target compensation amount and the initial density detection model;

[0015] The detection value determination module is used to obtain the coal preparation suspension density detection value based on the collected target pressure difference original signal, the target pressure original signal, and the coal preparation suspension density detection model.

[0016] According to another aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned method for detecting the density of the coal preparation suspension is implemented.

[0017] According to another aspect of the present application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the above-mentioned coal preparation suspension density detection method when executing the program.

[0018] By means of the above technical scheme, the present application provides a method and device for detecting the density of a coal preparation suspension, a storage medium, and a computer device. First, the historical pressure difference signal, the historical pressure signal, and the historical density test value of the coal preparation suspension corresponding to the historical sampling moment can be obtained. Further, the pressure difference compensation coefficient, the pressure compensation coefficient, and the target compensation amount in the initial density detection model can be determined based on the historical pressure difference signal, the historical pressure signal, and the historical density test value of the coal preparation suspension corresponding to each historical sampling moment. After obtaining the pressure difference compensation coefficient, the pressure compensation coefficient, and the target compensation amount, the pressure difference compensation coefficient, the pressure compensation coefficient, and the target compensation amount can all be substituted into the initial density detection model, and then the coal preparation suspension density detection model can be obtained. After obtaining the coal preparation suspension density detection model, the coal preparation suspension density detection value at the coal preparation production site can be obtained by calculating the coal preparation suspension density detection model based on the target pressure difference original signal and the target pressure original signal collected by the sensor. The embodiment of the present application determines the coal preparation suspension density detection model, and subsequently calculates the coal preparation suspension density detection value based on the target pressure difference original signal and the target pressure original signal collected by the sensor. The density of the coal preparation suspension can be detected quickly and accurately in real time while considering multiple influencing factors.

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 A schematic flow chart of a method for detecting density of a coal preparation suspension provided in an embodiment of the present application is shown;

[0022] Figure 2 A schematic flow chart of another method for detecting density of a coal preparation suspension provided in an embodiment of the present application is shown;

[0023] Figure 3 A schematic diagram showing the detection effect of a method for detecting the density of a coal preparation suspension provided in an embodiment of the present application is shown;

[0024] Figure 4 A schematic structural diagram of a coal preparation suspension density detection device provided in an embodiment of the present application is shown;

[0025] Figure 5An industrial application hardware architecture diagram of a method for detecting density of a coal preparation suspension provided in an embodiment of the present application is shown;

[0026] Figure 6 An industrial application software architecture diagram of a coal preparation suspension density detection method provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0027] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0028] In this embodiment, a method for detecting the density of a coal preparation suspension is provided. Figure 1 As shown, the method includes:

[0029] Step 101, obtaining a historical pressure difference signal, a historical pressure signal and a historical density test value of the coal preparation suspension corresponding to a historical sampling time;

[0030] The coal preparation suspension density detection method provided by the embodiment of the present application can be applied to the scene of coal preparation production, and the density of the coal preparation suspension can be determined in real time and accurately. First, the historical pressure difference signal, historical pressure signal and historical density test value of the coal preparation suspension corresponding to the historical sampling time can be obtained, that is, each group of historical pressure difference signal, historical pressure signal and historical density test value of the coal preparation suspension corresponds to a historical sampling time. Here, the historical pressure difference signal and the historical pressure signal can be signals directly collected by the pressure difference sensor and the pressure sensor installed in the coal preparation suspension, or they can be processed signals. The historical density test value of the coal preparation suspension can be obtained after the staff samples the coal preparation suspension at the historical sampling time and tests the coal preparation suspension sample. The manual sampling offline test method has the characteristics of being simple, accurate and cheap. However, the test cycle of the manual test density data is relatively long, and the manual test data often has a large lag, and timely online detection cannot be achieved, so that the manual test data is difficult to form a closed-loop analysis with other key production parameters in the integrated control system, and the closed-loop control of the coal preparation density cannot be achieved. Therefore, the embodiment of the present application helps determine the coal preparation suspension density detection model through the historical density test value of the coal preparation suspension.

[0031] Step 102, determining a pressure difference compensation coefficient, a pressure compensation coefficient and a target compensation amount corresponding to an initial density detection model based on the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension;

[0032] In this embodiment, further, the pressure difference compensation coefficient, pressure compensation coefficient, and target compensation amount in the initial density detection model can be determined based on the historical pressure difference signal, historical pressure signal, and historical density test value of the coal preparation suspension corresponding to each historical sampling moment. Here, the pressure difference compensation coefficient, pressure compensation coefficient, and target compensation amount are model parameters of the initial density detection model.

[0033] Step 103, obtaining a coal preparation suspension density detection model according to the pressure difference compensation coefficient, the pressure compensation coefficient, the target compensation amount and the initial density detection model;

[0034] In this embodiment, after the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount are obtained, the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount can all be substituted into the initial density detection model, and then the coal preparation suspension density detection model can be obtained. That is, the corresponding unknown quantities in the initial density detection model are replaced by the obtained pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount, and the coal preparation suspension density detection model can be obtained.

[0035] Step 104, obtaining a coal preparation suspension density detection value based on the collected target pressure difference original signal, target pressure original signal, and the coal preparation suspension density detection model.

[0036] In this embodiment, after obtaining the coal preparation suspension density detection model, the coal preparation suspension density detection value at the coal preparation production site can be obtained by calculating the coal preparation suspension density detection model based on the target pressure difference original signal and the target pressure original signal collected by the sensor.

[0037] By applying the technical solution of this embodiment, first, the historical pressure difference signal, historical pressure signal and historical density test value of the coal preparation suspension corresponding to the historical sampling moment can be obtained. Further, the pressure difference compensation coefficient, pressure compensation coefficient and target compensation amount in the initial density detection model can be determined based on the historical pressure difference signal, historical pressure signal and historical density test value of the coal preparation suspension corresponding to each historical sampling moment. After obtaining the pressure difference compensation coefficient, pressure compensation coefficient and target compensation amount, the pressure difference compensation coefficient, pressure compensation coefficient and target compensation amount can all be substituted into the initial density detection model, and then the coal preparation suspension density detection model can be obtained. After obtaining the coal preparation suspension density detection model, the coal preparation suspension density detection value at the coal preparation production site can be obtained by calculating the coal preparation suspension density detection model based on the target pressure difference original signal and target pressure original signal collected by the sensor. The embodiment of the present application determines the coal preparation suspension density detection model, and then calculates the coal preparation suspension density detection value according to the target pressure difference original signal and the target pressure original signal collected by the sensor in real time. The density of the coal preparation suspension can be detected quickly and accurately in real time while considering multiple influencing factors.

[0038] Further, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, another method for detecting the density of a coal preparation suspension is provided, the method comprising:

[0039] Step 201, obtaining a historical pressure difference original signal and a historical pressure original signal, and performing signal filtering processing on the historical pressure difference original signal and the historical pressure original signal through the Laida criterion; performing first-order inertial filtering processing on the filtered historical pressure difference original signal and the historical pressure original signal to obtain a historical pressure difference signal and a historical pressure signal; obtaining a historical density test value of the coal preparation suspension, and performing time series calibration processing on the historical density test value of the coal preparation suspension with the historical pressure difference signal and the historical pressure signal to obtain the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension corresponding to each historical sampling moment;

[0040] In this embodiment, the historical pressure difference original signal and the historical pressure original signal can be directly collected by the pressure difference sensor and the pressure sensor, and can be stored in the database after collection. Here, the historical pressure difference original signal can be ΔP(k), and the historical pressure original signal can be P(k), where k represents the historical sampling time. First, the historical pressure difference original signal and the historical pressure original signal are filtered using the Laida criterion. Specifically, the historical pressure difference original signal and the historical pressure original signal can be arranged in time series, and outliers can be removed in the sliding time window using the Laida criterion. Here, the Bessel formula can be used to calculate the standard error σ in the Laida criterion (3σ): Among them, x i is the original signal, which can be either the original signal of historical pressure difference or the original signal of historical pressure. n is the sample size, which can be the sample size corresponding to the width of each sliding time window. is the mean of n groups of samples. After being processed by the Laida criterion, the filtered historical pressure difference original signal and the historical pressure original signal can also be subjected to first-order inertial filtering. Here, the first-order inertial filtering function can be X(n)=αx(n)+(1-α)x(n-1), where α is the filtering coefficient, which can be 0.85, x(n) is the current sampling value, x(n-1) is the last filtering output value, and X(n) is the current filtering output value. After being processed by the Laida criterion and the first-order inertial filtering, data outliers can be eliminated and the impact of data noise can be reduced.

[0041] Next, the historical density test value of the coal preparation suspension can be obtained from the database, and the historical density test value of the coal preparation suspension, the historical pressure difference signal, and the historical pressure signal can be time-series benchmarked, that is, for each historical sampling moment, the historical pressure difference signal, the historical pressure signal, and the historical density test value of the coal preparation suspension corresponding to the historical sampling moment can be found. Here, since the sampling time interval of the manual test is much longer than the sampling time interval of the sensor, the time when the coal preparation suspension is manually sampled can be used as the historical sampling moment, and the historical pressure difference signal and the historical pressure signal corresponding to the historical sampling moment can be found and marked from the historical pressure difference signal and the historical pressure signal, so as to obtain the historical pressure difference signal, the historical pressure signal, and the historical density test value of the coal preparation suspension corresponding to each historical sampling moment.

[0042] Step 202, obtaining a historical pressure difference signal, a historical pressure signal and a historical density test value of the coal preparation suspension corresponding to the historical sampling time;

[0043] In this embodiment, the historical pressure difference signal, historical pressure signal and historical density test value of the coal preparation suspension corresponding to the historical sampling moment can be obtained, that is, each group of historical pressure difference signal, historical pressure signal and historical density test value of the coal preparation suspension corresponds to a historical sampling moment.

[0044] Step 203, determining the pressure difference signal input order and the pressure signal input order; based on the pressure difference signal input order, processing the historical pressure difference signal corresponding to each of the historical sampling moments, respectively, to obtain a processed historical pressure difference signal; based on the pressure signal input order, processing the historical pressure signal corresponding to each of the historical sampling moments, respectively, to obtain a processed historical pressure signal;

[0045] In this embodiment, the pressure difference signal input order and the pressure signal input order can be determined first, and then the historical pressure difference signal and the historical pressure signal can be processed according to the pressure difference signal input order and the pressure signal input order respectively. Specifically, ΔP′(k) can represent the processed historical pressure difference signal, which can be specifically expressed by the formula: For processing, n2 is the input order of the pressure difference signal; P′(k) can represent the processed historical pressure signal, which can be specifically expressed by the formula Processing is performed, wherein n1 is the pressure signal input order. The embodiment of the present application processes the historical pressure difference signal and the historical pressure signal according to the pressure difference signal input order and the pressure signal input order, which can make the signal smoother and help to eliminate abnormal values.

[0046] Step 204, constructing a target parameter estimation equation based on the initial density detection model;

[0047] In this embodiment, the target parameter estimation equation corresponding to the initial density detection model can be constructed based on the initial density detection model. Here, the target parameter estimation equation can include the pressure difference compensation coefficient, the pressure compensation coefficient, and the unknown number corresponding to the target compensation amount.

[0048] In the embodiment of the present application, the initial density detection model can be Among them, ΔP′(k) is the processed historical pressure difference signal, g is the gravity acceleration g=9.8N / kg, △h is the installation height of the differential pressure transmitter, P′(k) is the processed historical pressure signal, B is the pressure difference compensation coefficient, B1 is the pressure compensation coefficient, and B2 is the target compensation amount.

[0049] In the embodiment of the present application, the parameters of the coal preparation suspension density detection model can be identified based on any system identification method. Specifically, the least squares system identification method can be selected. First, the initial density detection model is estimated based on the minimization of the mean square error, that is, the corresponding target parameter estimation equation can be Among them, y i =ρ a(i) is the historical density test value of the coal preparation suspension, and m is the number of the historical density test values ​​of the coal preparation suspension. Here, the number of the historical density test values ​​of the coal preparation suspension is equal to the number of the historical pressure difference signals and the historical pressure signals.

[0050] Step 205, deriving the target parameter estimation equation according to the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount, respectively, to obtain derivatives corresponding to the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount;

[0051] In this embodiment, since the target parameter estimation equation includes the pressure difference compensation coefficient, the pressure compensation coefficient and the unknowns corresponding to the target compensation amount, the target parameter estimation equation can be differentiated. Specifically, the derivatives can be taken based on the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount to obtain the derivative corresponding to the pressure difference compensation coefficient, the derivative corresponding to the pressure compensation coefficient and the derivative corresponding to the target compensation amount.

[0052] Specifically, solve B, B1, and B2 so that Minimize Divide into the derivation of B, B1 and B2, and get as well as

[0053] Step 206, determining the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount corresponding to when the derivative is zero based on the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension;

[0054] In this embodiment, after obtaining the derivatives corresponding to the pressure difference compensation coefficient, the pressure compensation coefficient, and the target compensation amount, the pressure difference compensation coefficient, the pressure compensation coefficient, and the target compensation amount corresponding to each derivative being zero can be obtained based on the historical pressure difference signal, the historical pressure signal, and the historical density test values ​​of the coal preparation suspension.

[0055] Specifically, setting the above equation to zero, we can get the solutions of B, B1 and B2 respectively: as well as Then, the pressure difference compensation coefficient, pressure compensation coefficient and target compensation amount can be obtained.

[0056] Step 207, obtaining a coal preparation suspension density detection model according to the pressure difference compensation coefficient, the pressure compensation coefficient, the target compensation amount and the initial density detection model;

[0057] In this embodiment, after the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount are obtained, the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount can all be substituted into the initial density detection model, and then the coal preparation suspension density detection model can be obtained. That is, the corresponding unknown quantities in the initial density detection model are replaced by the obtained pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount, and the coal preparation suspension density detection model can be obtained.

[0058] Step 208, obtaining a coal preparation suspension density detection value based on the collected target pressure difference original signal, target pressure original signal, and the coal preparation suspension density detection model.

[0059] In this embodiment, after obtaining the coal preparation suspension density detection model, the target pressure difference original signal and the target pressure original signal collected by the sensor can be used as the basis, and the coal preparation suspension density detection value at the coal preparation production site can be detected in real time through the calculation of the coal preparation suspension density detection model. Here, the target pressure difference original signal and the target pressure original signal collected by the sensor can also be processed by the Laida criterion, the first-order inertial filter, etc., and then input into the coal preparation suspension density detection model to obtain the coal preparation suspension density detection value.

[0060] In an embodiment of the present application, optionally, after "obtaining the coal preparation suspension density detection model" in step 207, the method also includes: determining a first target test value corresponding to the target sampling time, and based on the target sampling time, determining multiple second target test values ​​from historical test values; determining multiple target density detection values ​​corresponding to the first target test value and the second target test value, and determining a target deviation value based on the first target test value, the second target test value and the multiple target density detection values; when the target deviation value is greater than a preset deviation threshold, determining a pressure difference compensation update coefficient, a pressure compensation update coefficient and a target compensation update amount of the coal preparation suspension density detection model, and updating the coal preparation suspension density detection model based on the pressure difference compensation update coefficient, the pressure compensation update coefficient and the target compensation update amount.

[0061] In this embodiment, after determining the density detection model of the coal preparation suspension, the subsequent staff can also sample the coal preparation suspension according to the target sampling time interval and test the sample to update the density detection model of the coal preparation suspension according to the test value. Here, the time when the staff samples the coal preparation suspension each time can be used as the target sampling time, and a first target test value can be determined correspondingly at each target sampling time. The first target test value is the density test value obtained after testing the coal preparation suspension sample at the target sampling time. After determining the first target test value, multiple second target test values ​​can also be determined from the historical test values ​​based on the target sampling time. Then, the target density detection value corresponding to the first target test value and multiple target density detection values ​​corresponding to the multiple second target test values ​​can be determined. Here, the target density detection value is the density value calculated by the coal preparation suspension density detection model at the same time as the target test value. After that, the target deviation value is calculated by the first target test value, the second target test value, and the multiple corresponding target density detection values. For example, the cumulative sliding time window width corresponds to (M+1) target test values Among them, ρ a (T) may be the first target assay value, ρ a (T-1)……ρ a (TM) can be multiple second target test values, and the Laida criterion (3σ) error correction mechanism is introduced to eliminate the influence of abnormal test values. Target density detection value When the target deviation value θ(T) exceeds the preset deviation threshold δ, that is, θ(T)>δ, the pressure difference compensation update coefficient, pressure compensation update coefficient and target compensation update amount can be determined, and the coal preparation suspension density detection model can be updated through the pressure difference compensation update coefficient, pressure compensation update coefficient and target compensation update amount, that is, the model parameters can be corrected, which can be achieved through the parameter on-site / remote correction mode, where the pressure difference compensation update coefficient, pressure compensation update coefficient and target compensation update amount are the update parameters of the coal preparation suspension density detection model. Here, θ(T) can be: The embodiment of the present application determines the target deviation value based on the first target test value corresponding to the target sampling time, and when the target deviation value is greater than the preset deviation threshold, the coal preparation suspension density detection model is updated at any time, which can make the coal preparation suspension density detection model more accurate. In this embodiment, as the artificial density test value increases, the model parameters in the coal preparation suspension density detection model can be corrected in an on-site / remote manner.

[0062] In an embodiment of the present application, optionally, the "determining the pressure difference compensation update coefficient, the pressure compensation update coefficient and the target compensation update amount of the coal preparation suspension density detection model" includes: determining the pressure difference compensation update coefficient, the pressure compensation update coefficient and the target compensation update amount based on the first target test value, the first pressure difference original signal and the first pressure original signal corresponding to the first target test value, and the historical test value, the second pressure difference original signal and the second pressure original signal corresponding to the historical test value.

[0063] In this embodiment, when determining the pressure difference compensation update coefficient, the pressure compensation update coefficient, and the target compensation update amount, the above-mentioned method for determining the pressure difference compensation coefficient, the pressure compensation coefficient, and the target compensation amount can also be used. Specifically, the pressure difference compensation update coefficient, the pressure compensation update coefficient, and the target compensation update amount can be determined based on the first target test value, the first pressure difference original signal corresponding to the first target test value, the first pressure original signal, and the historical test value, the second pressure difference original signal corresponding to the historical test value, and the second pressure original signal. Then, the corresponding parameters in the coal preparation suspension density detection model can be updated to obtain the updated coal preparation suspension density detection model.

[0064] In the embodiment of the present application, optionally, the method further includes: when the target deviation value is less than or equal to the preset deviation threshold, maintaining the coal preparation suspension density detection model unchanged.

[0065] In this embodiment, when the target deviation value is less than or equal to the preset deviation threshold, it indicates that the accuracy of the coal preparation suspension density detection model is relatively high. At this time, the coal preparation suspension density detection model can be kept unchanged and continued to be used.

[0066] Figure 2 FIG. 1 shows a schematic diagram of an execution flow of a method for detecting density of a coal preparation suspension provided in an embodiment of the present application, such as Figure 2 As shown, the process can be described as follows:

[0067] The differential pressure signal ΔP(k) collected by the differential pressure sensor and the pressure signal P(k) collected by the pressure sensor are obtained, and the differential pressure signal and the pressure signal are sent to the data acquisition and communication module. The data acquisition and communication module sends the differential pressure signal and the pressure signal to the data storage module, and the data storage module stores them. Then, the data processing module processes the differential pressure signal and the pressure signal according to the Laida criterion, the first-order inertial filtering, the input order of the differential pressure signal and the input order of the pressure signal, etc., and outputs ΔP′(k) and P′(k). Finally, the parameter identification model determines the model parameters (differential pressure compensation coefficient, pressure compensation coefficient and target compensation amount) of the coal preparation suspension density detection model according to ΔP′(k) and P′(k), and then substitutes the obtained model parameters into the initial density detection model to obtain the coal preparation suspension density detection model. Subsequently, the intelligent density detection value can be obtained according to the differential pressure signal, the pressure signal and the coal preparation suspension density detection model collected by the sensor.

[0068] In addition, after obtaining the coal preparation suspension density detection model, the coal preparation suspension density detection model can be updated in real time. Specifically, one of the two methods, local or remote, can be selected to update the model parameters. For example, when updating the model parameters, the pressure difference signal ΔP(k) collected by the pressure difference sensor, the pressure signal P(k) collected by the pressure sensor, and the artificial density test value ρ a (T) is sent to the remote correction module, which then can realize remote automatic correction of the model parameters and send the new model parameters to the identification model to obtain an updated coal preparation suspension density detection model.

[0069] The method for detecting the density of the coal preparation suspension provided in the embodiment of the present application has a high detection accuracy. The detection effect and the instrument effect are compared by introducing evaluation indicators: Root mean square error: the expected value of the square root of the difference between the intelligent detection value (or instrument value) and the test value at the corresponding test time. Qualification rate indicator |P|: the percentage of samples whose absolute error between the intelligent detection value (or instrument value) and the density test value at the corresponding test time is within ±0.01g / cm3 (|P|<0.01) to the total number of samples. By Figure 3 It can be seen that through long-term observation, the RMSE of the density intelligent detection value corresponding to the coal preparation suspension density detection method provided in the embodiment of the present application compared with the manual test value is 0.0058; the qualified rate |P|<0.01 reaches 94.12%, and the detection effect is good.

[0070] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides a coal preparation suspension density detection device, such as Figure 4 As shown, the device comprises:

[0071] An acquisition module is used to acquire a historical pressure difference signal, a historical pressure signal and a historical density test value of the coal preparation suspension corresponding to a historical sampling moment;

[0072] A numerical determination module, for determining a pressure difference compensation coefficient, a pressure compensation coefficient and a target compensation amount corresponding to an initial density detection model based on the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension;

[0073] A model determination module, used for obtaining a coal preparation suspension density detection model according to the pressure difference compensation coefficient, the pressure compensation coefficient, the target compensation amount and the initial density detection model;

[0074] The detection value determination module is used to obtain the coal preparation suspension density detection value based on the collected target pressure difference original signal, the target pressure original signal, and the coal preparation suspension density detection model.

[0075] Optionally, the value determination module includes:

[0076] An equation building unit, used to build a target parameter estimation equation based on the initial density detection model;

[0077] a derivation unit, configured to derive the target parameter estimation equation according to the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount, respectively, to obtain derivatives corresponding to the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount;

[0078] A numerical determination unit is used to determine the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount corresponding to when the derivative is zero based on the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension.

[0079] Optionally, the device further comprises:

[0080] An order determination module, used for determining the pressure difference signal input order and the pressure signal input order before determining the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount corresponding to when the derivative is zero;

[0081] A signal processing module is used to process the historical pressure difference signal corresponding to each of the historical sampling moments based on the pressure difference signal input order to obtain a processed historical pressure difference signal; based on the pressure signal input order, process the historical pressure signal corresponding to each of the historical sampling moments to obtain a processed historical pressure signal.

[0082] Optionally, the device further comprises:

[0083] The filtering processing module is also used to obtain the historical pressure difference original signal and the historical pressure original signal before obtaining the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension corresponding to the historical sampling time, and perform signal filtering processing on the historical pressure difference original signal and the historical pressure original signal by Laida criterion;

[0084] A filtering processing module is used to perform first-order inertial filtering on the filtered historical pressure difference original signal and the historical pressure original signal to obtain a historical pressure difference signal and a historical pressure signal;

[0085] The acquisition module is also used to obtain the historical density test value of the coal preparation suspension, and perform time-series alignment processing on the historical density test value of the coal preparation suspension, the historical pressure difference signal and the historical pressure signal, so as to obtain the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension corresponding to each historical sampling moment.

[0086] Optionally, the device further comprises:

[0087] An assay value determination module is used to determine a first target assay value corresponding to a target sampling time after obtaining the coal preparation suspension density detection model, and determine a plurality of second target assay values ​​from historical assay values ​​based on the target sampling time;

[0088] a deviation value determination module, configured to determine a plurality of target density detection values ​​corresponding to the first target test value and the second target test value, and determine a target deviation value based on the first target test value, the second target test value and the plurality of target density detection values;

[0089] An updating module is used to determine the pressure difference compensation update coefficient, the pressure compensation update coefficient and the target compensation update amount of the coal preparation suspension density detection model when the target deviation value is greater than a preset deviation threshold, and to update the coal preparation suspension density detection model based on the pressure difference compensation update coefficient, the pressure compensation update coefficient and the target compensation update amount.

[0090] Optionally, the update module is used to determine the pressure difference compensation update coefficient, the pressure compensation update coefficient and the target compensation update amount based on the first target test value, the first pressure difference original signal and the first pressure original signal corresponding to the first target test value, and the historical test value, the second pressure difference original signal and the second pressure original signal corresponding to the historical test value.

[0091] Optionally, the device further comprises:

[0092] The model maintaining module is used to maintain the coal preparation suspension density detection model unchanged when the target deviation value is less than or equal to the preset deviation threshold.

[0093] It should be noted that for other corresponding descriptions of the functional units involved in the coal preparation suspension density detection device provided in the embodiment of the present application, reference can be made to Figure 1 The corresponding description in the method will not be repeated here.

[0094] Further, optionally, in the embodiment of the present application, if Figure 5 As shown in the figure, the industrial application hardware platform of the coal preparation suspension density detection model may include: differential pressure sensor, pressure sensor, instrument box, signal isolator, logic controller (PLC), switch, touch screen, communication equipment, etc. Among them, probe 1 and probe 2 are differential pressure probes, and probe 3 is a pressure probe. The installation positions of probe 2 and probe 3 can be exchanged according to the actual production conditions. The signal isolator, PLC, switch, touch screen and communication module are deployed in the instrument box. PLC is used to realize intelligent real-time detection of coal preparation suspension density based on multiple input information; the touch screen is used to realize the functions of local display, parameter setting, local parameter update, and local / remote parameter correction mode switching of coal preparation suspension density detection value; the communication module is based on the communication between the switch, touch screen and PLC, and is used to realize data reading and remote model update parameter writing, that is, to realize remote parameter correction of coal preparation suspension density detection model. At the same time, PLC is connected to the on-site DCS to realize real-time display and data management of coal preparation suspension density detection value.

[0095] Industrial sensors (differential pressure sensors, pressure sensors) are connected to the transmitter through pressure pipes, and the transmitter is connected to the isolator in the instrument box through hard lines. The isolator transmits the signal to the PLC to realize communication from the transmitter to the PLC; the PLC, touch screen, and communication module in the density meter instrument box are in the same local area network, and data is transmitted to each other through the TCP / IP protocol; the PLC communicates with the on-site DCS through hard lines; the remote correction module communicates with the device in the on-site instrument box through a wireless network, so that the data and test results of the industrial site can be uploaded to the "cloud" and centralized data management can be achieved.

[0096] Optionally, in the embodiment of the present application, Figure 6As shown, the industrial application software platform of the coal preparation suspension density detection model can include two parts: software front-end human-computer interaction and background function realization. Specifically, the WinCC FlexibleSmart application software platform can be used to build a front-end human-computer interaction system; STEP 7-MicroWIN SMART and Python software platforms can be used to build data acquisition and communication, multi-input information coal preparation suspension density intelligent detection and remote correction system. Among them, the front-end human-computer interaction interface (touch screen) is developed based on the WinCC Flexible Smart application software platform to realize human-computer interaction; the background PLC is edited using the STEP 7-MicroWIN SMART software platform to realize the intelligent detection of coal preparation suspension density based on multi-input information; the remote parameter correction function is developed using the Python software platform, and the software platform communicates with the PLC and touch screen through the communication module to read key data and write model update parameters.

[0097] Based on the above Figure 1 The method shown in the embodiment of the present application is accordingly provided with a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned Figure 1 The coal preparation suspension density detection method is shown.

[0098] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0099] Based on the above Figure 1 The method shown, and Figure 4 In order to achieve the above-mentioned purpose, the embodiment of the present application further provides a computer device, which can be a personal computer, a server, a network device, etc. The computer device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 The coal preparation suspension density detection method is shown.

[0100] Optionally, the computer device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a WI-FI interface), etc.

[0101] Those skilled in the art will appreciate that the computer device structure provided in this embodiment does not limit the computer device, and may include more or fewer components, or a combination of certain components, or different component arrangements.

[0102] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages and saves the hardware and software resources of the computer device, and supports the operation of information processing programs and other software and / or programs. The network communication module is used to realize communication between the components inside the storage medium, and communication with other hardware and software in the physical device.

[0103] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform, or by hardware. First, the historical pressure difference signal, historical pressure signal and historical density test value of the coal preparation suspension corresponding to the historical sampling time can be obtained. Further, the pressure difference compensation coefficient, pressure compensation coefficient and target compensation amount in the initial density detection model can be determined based on the historical pressure difference signal, historical pressure signal and historical density test value of the coal preparation suspension corresponding to each historical sampling time. After obtaining the pressure difference compensation coefficient, pressure compensation coefficient and target compensation amount, the pressure difference compensation coefficient, pressure compensation coefficient and target compensation amount can all be substituted into the initial density detection model, and then the coal preparation suspension density detection model can be obtained. After obtaining the coal preparation suspension density detection model, the target pressure difference original signal and target pressure original signal collected by the sensor can be used to calculate the coal preparation suspension density detection model to obtain the coal preparation suspension density detection value at the coal preparation production site. The embodiment of the present application determines the coal preparation suspension density detection model, and subsequently calculates the coal preparation suspension density detection value based on the target pressure difference original signal and the target pressure original signal collected by the sensor. The density of the coal preparation suspension can be detected quickly and accurately in real time while considering multiple influencing factors.

[0104] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the description of the implementation scenario, or can be changed accordingly and located in one or more devices different from the present implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple submodules.

[0105] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.

Claims

1. A method for detecting the density of a coal preparation suspension, It is characterized in that include: Obtain the historical differential pressure signal, historical pressure signal and historical density test value of the coal preparation suspension corresponding to the historical sampling time; Based on the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension, determine the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount corresponding to the initial density detection model; According to the pressure difference compensation coefficient, the pressure compensation coefficient, the target compensation amount and the initial density detection model, a coal preparation suspension density detection model is obtained, wherein the parameters of the coal preparation suspension density detection model are identified based on an arbitrary system identification method; Based on the collected target pressure difference original signal, target pressure original signal, and the coal preparation suspension density detection model, a coal preparation suspension density detection value is obtained; The initial density detection model is: ； ； ； in, is the processed historical differential pressure signal, g is the gravity acceleration, △h is the installation height of the differential pressure transmitter, is the processed historical pressure signal, B is the pressure difference compensation coefficient, and B 1 is the pressure compensation coefficient, B 2 is the target compensation amount, n 2 is the input order of the pressure difference signal, n 1 is the input order of the pressure signal, and k represents the historical sampling time.

2. The method according to claim 1, It is characterized in that The method for identifying any system includes a least squares system identification method; when the least squares system identification method is adopted, the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount corresponding to the initial density detection model are determined based on the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension, including: Based on the initial density detection model, construct a target parameter estimation equation; Deriving the target parameter estimation equation according to the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount, respectively, to obtain derivatives corresponding to the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount; Based on the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension, the pressure difference compensation coefficient, the pressure compensation coefficient and the target compensation amount corresponding to when the derivative is zero are determined.

3. The method according to claim 2, It is characterized in that Before determining the pressure difference compensation coefficient, the pressure compensation coefficient, and the target compensation amount corresponding to when the derivative is zero, the method further includes: Determine the input order of the differential pressure signal and the input order of the pressure signal; Based on the pressure difference signal input order, the historical pressure difference signal corresponding to each historical sampling moment is processed respectively to obtain a processed historical pressure difference signal; Based on the pressure signal input order, the historical pressure signal corresponding to each historical sampling moment is processed respectively to obtain a processed historical pressure signal.

4. The method according to claim 1, It is characterized in that Before obtaining the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension corresponding to the historical sampling time, the method further includes: Acquire a historical pressure difference original signal and a historical pressure original signal, and perform signal filtering processing on the historical pressure difference original signal and the historical pressure original signal by Laida criterion; Performing first-order inertial filtering on the filtered historical pressure difference original signal and the historical pressure original signal to obtain a historical pressure difference signal and a historical pressure signal; The historical density test value of the coal preparation suspension is obtained, and the historical density test value of the coal preparation suspension is time-series aligned with the historical pressure difference signal and the historical pressure signal to obtain the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension corresponding to each historical sampling moment.

5. The method according to claim 1, It is characterized in that After obtaining the coal preparation suspension density detection model, the method further comprises: Determine a first target test value corresponding to a target sampling time, and determine a plurality of second target test values ​​from historical test values ​​based on the target sampling time; Determining a plurality of target density detection values ​​corresponding to the first target assay value and the second target assay value, and determining a target deviation value based on the first target assay value, the second target assay value, and the plurality of target density detection values; When the target deviation value is greater than a preset deviation threshold, the pressure difference compensation update coefficient, the pressure compensation update coefficient and the target compensation update amount of the coal preparation suspension density detection model are determined, and the coal preparation suspension density detection model is updated based on the pressure difference compensation update coefficient, the pressure compensation update coefficient and the target compensation update amount.

6. The method according to claim 5, It is characterized in that The step of determining the pressure difference compensation update coefficient, the pressure compensation update coefficient and the target compensation update amount of the coal preparation suspension density detection model comprises: The pressure difference compensation update coefficient, the pressure compensation update coefficient and the target compensation update amount are determined based on the first target test value, the first pressure difference original signal and the first pressure original signal corresponding to the first target test value, and the historical test value, the second pressure difference original signal and the second pressure original signal corresponding to the historical test value.

7. The method according to claim 5, It is characterized in that The method further comprises: When the target deviation value is less than or equal to the preset deviation threshold, the coal preparation suspension density detection model is kept unchanged.

8. A coal preparation suspension density detection device, It is characterized in that include: An acquisition module is used to acquire a historical pressure difference signal, a historical pressure signal and a historical density test value of the coal preparation suspension corresponding to a historical sampling moment; A numerical determination module, for determining a pressure difference compensation coefficient, a pressure compensation coefficient and a target compensation amount corresponding to an initial density detection model based on the historical pressure difference signal, the historical pressure signal and the historical density test value of the coal preparation suspension; A model determination module, for obtaining a coal preparation suspension density detection model according to the pressure difference compensation coefficient, the pressure compensation coefficient, the target compensation amount and the initial density detection model, wherein the parameters of the coal preparation suspension density detection model are identified based on an arbitrary system identification method; A detection value determination module, used for obtaining a coal preparation suspension density detection value based on the collected target pressure difference original signal, the target pressure original signal, and the coal preparation suspension density detection model; The initial density detection model is: ； ； ； in, is the processed historical differential pressure signal, g is the gravity acceleration, △h is the installation height of the differential pressure transmitter, is the processed historical pressure signal, B is the pressure difference compensation coefficient, and B 1 is the pressure compensation coefficient, B 2 is the target compensation amount, n 2 is the input order of the pressure difference signal, n 1 is the input order of the pressure signal, and k represents the historical sampling time.

9. A storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, It is characterized in that When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images