A monitoring and control method for sand and gravel separator

Abstract

The present invention discloses a monitoring and control method for a sand and gravel separator, wherein the first image information is obtained through an image acquisition device, the first image information including the total amount of sand and gravel to be separated; the sand and gravel amount information is obtained according to the first image information; the sand and gravel amount information is input into an evaluation model to obtain water injection amount information; a torsional strength rule list is obtained, the torsional strength rule list including the correspondence between the sand and gravel mixed liquid to be stirred, the torsional strength and the separation result; based on the torsional strength rule list, the predicted torsional strength information is obtained according to the water injection amount information and the sand and gravel amount information; a torsional control strategy is obtained according to the predicted torsional strength information, and the stirring speed of the sand and gravel separator is controlled according to the torsional control strategy. The method solves the technical problem that the sand and gravel separator in the prior art operates according to a predetermined mode without considering the specific characteristics of the separated sand and gravel, and thus has a poor sand and gravel separation effect and uncontrollable energy loss.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a monitoring and control method for a sand and gravel separator. Background Art

[0002] When in use, the sand and gravel separator is mainly used to clean the mixer truck and recycle the sand and gravel in it. This can effectively avoid the pollution caused by concrete, etc., and at the same time, it can also solve the use of building materials to a certain extent. The water pump draws clean water and injects it into the mixer truck. After washing, the sewage and residue will be poured into the drainage trough of the car wash. After that, the water pump will draw the sewage in the mixing tank and form a high-speed flow of water to rush into the sand and gravel separation equipment; sand and stone will be separated from the sewage, so they can become the raw materials for mixing concrete again. How to achieve effective separation of sand and gravel is the main consideration of the sand and gravel separator. In the existing technology, the sand and gravel separator operates according to the established mode without considering the specific characteristics of the separated sand and gravel. Therefore, there are technical problems such as poor sand and gravel separation effect and uncontrollable energy loss. Summary of the invention

[0003] The present invention aims to solve the above technical defects by providing a monitoring and control method for a sand and gravel separator, so as to solve the technical problem that the sand and gravel separator in the prior art operates according to a predetermined mode without considering the specific characteristics of the separated sand and gravel, resulting in poor sand and gravel separation effect and uncontrollable energy loss. The separation control corresponding to the specific state of the sand and gravel to be separated is achieved, which not only ensures the separation effect of the sand and gravel, but also avoids unnecessary energy consumption and wear of the equipment. At the same time, the analysis and calculation process adds artificial intelligence technology to improve the calculation efficiency and result accuracy through machine learning.

[0004] To this end, the first object of the present invention is to propose a monitoring and control method for a sand and gravel separator, the method is applied to a monitoring and control system, the system includes a monitoring and control device, the monitoring and control device includes an image acquisition device, the method includes: obtaining first image information through the image acquisition device, the first image information includes the total amount of sand and gravel to be separated; according to the first image information, obtaining sand and gravel amount information; inputting the sand and gravel amount information into an evaluation model to obtain water injection amount information; obtaining a torsional strength rule list, the torsional strength rule list includes the correspondence between the sand and gravel mixture to be stirred, the torsional strength and the separation result; based on the torsional strength rule list, according to the water injection amount information and the sand and gravel amount information, obtaining predicted torsional strength information; according to the predicted torsional strength information, obtaining a torsional control strategy, and controlling the stirring speed of the sand and gravel separator according to the torsional control strategy.

[0005] The second object of the present invention is to provide a monitoring and control system for a sand and gravel separator, the system comprising:

[0006] A first obtaining unit, the first obtaining unit is used to obtain first image information through an image acquisition device, wherein the first image information includes the total amount of sand and gravel to be separated;

[0007] a second obtaining unit, the second obtaining unit being used to obtain sand and gravel amount information according to the first image information;

[0008] a third obtaining unit, the third obtaining unit being used to input the sand and gravel amount information into an evaluation model to obtain water injection amount information;

[0009] A fourth obtaining unit, the fourth obtaining unit is used to obtain a torsion strength rule list, the torsion strength rule list including a correspondence between a sand-gravel mixture to be stirred, torsion strength, and a separation result;

[0010] a fifth obtaining unit, the fifth obtaining unit being used to obtain predicted torsional strength information based on the torsional strength rule list, according to the water injection amount information and the sand and gravel amount information;

[0011] The first execution unit is used to obtain a torsion control strategy according to the predicted torsion strength information, and control the stirring speed of the sand and gravel separator according to the torsion control strategy.

[0012] The third object of the present invention is to provide a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0013] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0014] 1. A monitoring and control method for a sand and gravel separator provided in an embodiment of the present invention, the method is applied to a monitoring and control system, the system includes a monitoring and control device, the monitoring and control device includes an image acquisition device, the method includes: obtaining first image information through the image acquisition device, the first image information includes the total amount of sand and gravel to be separated; obtaining sand and gravel amount information according to the first image information; inputting the sand and gravel amount information into an evaluation model to obtain water injection amount information; obtaining a torsional strength rule list, the torsional strength rule list includes the correspondence between the sand and gravel mixed liquid to be stirred, the torsional strength and the separation result; based on the torsional strength rule list, according to the water injection amount information and the sand and gravel amount information, obtaining predicted torsional strength information; according to the predicted torsional strength information, obtaining a torsional control strategy, and controlling the stirring speed of the sand and gravel separator according to the torsional control strategy. The corresponding separation control is achieved according to the specific state of the sand and gravel to be separated, which not only ensures the separation effect of sand and gravel, but also avoids unnecessary energy consumption and wear of the equipment. At the same time, artificial intelligence technology is added to the analysis and calculation process to improve the calculation efficiency and result accuracy through machine learning, thereby solving the technical problem that the sand and gravel separator in the prior art operates according to a predetermined mode without considering the specific characteristics of the separated sand and gravel, resulting in poor sand and gravel separation effect and uncontrollable energy loss.

[0015] 2. A monitoring and control method for a sand and gravel separator in an embodiment of the present application obtains a first sensing force set and a second sensing force set through a gravity sensor, wherein the first sensing force set corresponds to a first position area, and the second sensing force set corresponds to a second position area; a first uniformity and a second uniformity are obtained according to the first sensing force set and the second sensing force set, respectively; a judgment is made as to whether the first uniformity and the second uniformity satisfy a second predetermined condition, respectively, to obtain a judgment result; according to the judgment result, an adjustment control strategy is obtained to achieve real-time monitoring of the separation state, and timely adjustments are made for the separation effect that does not meet the requirements, so as to avoid rework due to poor separation, and ensure the technical effect of matching the separation effect with the separation machine operating parameter control.

[0016] 3. A monitoring and control method for a sand and gravel separator according to an embodiment of the present application obtains equipment force information according to the first sensing force set and the second sensing force set; obtains torsional strength information according to the torsion control strategy; inputs the equipment force information and torsional strength information into a loss prediction model; obtains a third output result of the loss prediction model, the third output result includes a predicted loss result; and obtains warning information when the predicted loss result exceeds a third preset condition. The technical effect of monitoring and evaluating the force during the operation of the separator, monitoring and warning the loss of equipment in the sand and gravel separator, and extending the service life of the equipment is achieved.

[0017] 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

[0018] Figure 1 This is a flow chart of a monitoring and control method for a sand and gravel separator according to an embodiment of the present application;

[0019] Figure 2 A schematic flow chart of another monitoring and control method for a sand and gravel separator in an embodiment of the present application;

[0020] Figure 3 A schematic flow chart of another monitoring and control method for a sand and gravel separator in an embodiment of the present application;

[0021] Figure 4 A schematic flow chart of another monitoring and control method for a sand and gravel separator in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of a monitoring and control system for a sand and gravel separator according to an embodiment of the present application;

[0023] Figure 6 It is a schematic diagram of the structure of an exemplary electronic device according to an embodiment of the present application.

[0024] Explanation of the reference numerals: first obtaining unit 11 , second obtaining unit 12 , third obtaining unit 13 , fourth obtaining unit 14 , fifth obtaining unit 15 , first executing unit 16 , bus 300 , receiver 301 , processor 302 , transmitter 303 , memory 304 , bus interface 305 . DETAILED DESCRIPTION

[0025] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limitations of the present invention. On the contrary, embodiments of the present invention include all changes, modifications and equivalents that fall within the spirit and connotation of the appended claims.

[0026] In the description of the present invention, it should be noted that any process or method description in the flowchart or otherwise described herein may be understood as representing a module, fragment or portion of a code comprising one or more executable instructions for implementing steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations, in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0027] A monitoring and control method for a sand and gravel separator according to an embodiment of the present invention will be described below with reference to the accompanying drawings.

[0028] The technical solution of the present application is: obtain first image information through an image acquisition device, the first image information includes the total amount of sand and gravel to be separated; obtain sand and gravel amount information based on the first image information; input the sand and gravel amount information into the evaluation model to obtain water injection amount information; obtain a torsional strength rule list, the torsional strength rule list includes the correspondence between the sand and gravel mixed liquid to be stirred, the torsional strength and the separation result; based on the torsional strength rule list, obtain the predicted torsional strength information according to the water injection amount information and the sand and gravel amount information; obtain the torsional control strategy according to the predicted torsional strength information, and control the stirring speed of the sand and gravel separator according to the torsional control strategy. The technical problem that the sand and gravel separator in the prior art operates according to a predetermined mode without considering the specific characteristics of the separated sand and gravel, and thus has poor sand and gravel separation effect and uncontrollable energy loss.

[0029] Embodiment 1

[0030] like Figure 1 As shown, an embodiment of the present application provides a monitoring and control method for a sand and gravel separator, the method is applied to a monitoring and control system, the system includes a monitoring and control device, the monitoring and control device includes an image acquisition device and a gravity sensor, and the method includes:

[0031] Specifically, the monitoring and control device is used to monitor and collect data during the monitoring process of the sand and gravel separator, and communicate and transmit the collected data to the monitoring and control system. The monitoring and control system analyzes and calculates the received data, obtains the corresponding control instructions, connects to the controller of the sand and gravel separator, sends the corresponding control adjustment instructions, and operates and controls the sand and gravel separator. The image acquisition device is a device for image acquisition, which acquires images of the sand and gravel, mixed liquid, separation results, etc. that need to be imaged. The gravity sensor is set on the side wall of the separator, and the gravity sensor senses and detects the pressure on the side wall of the separator.

[0032] Step S100: obtaining first image information through an image acquisition device, wherein the first image information includes the total amount of sand and gravel to be separated;

[0033] Specifically, images of the sand and gravel that need to be separated are collected through image acquisition equipment such as a camera. The first image information is an overall image of the sand and gravel to be separated, covering all states of the sand and gravel to be separated, including quantity and shape.

[0034] Step S200: obtaining sand and gravel amount information according to the first image information;

[0035] Further, such as Figure 2 As shown, the step S200 of obtaining the sand and gravel amount information according to the first image information includes:

[0036] Step S210: setting a first reference object, wherein the first reference object has a first weight;

[0037] Step S220: obtaining acquisition feature information according to the first image information;

[0038] Step S230: performing image acquisition on the first reference object based on the acquisition feature information to obtain third image information;

[0039] Step S240: extracting features from the first image information and the third image information to obtain first image features and second image features;

[0040] Step S250: obtaining a first corresponding relationship according to the first weight and the second image feature;

[0041] Step S260 obtains the gravel amount information based on the first corresponding relationship and the first image feature.

[0042] Specifically, the sand and gravel to be analyzed are usually located in a mixer truck, which is not convenient for measurement. At the same time, the measurement process is time-consuming and labor-intensive, and the error rate is large. In order to improve the rapid identification and measurement of the sand and gravel to be separated, the embodiment of the present application utilizes the processing and statistics of image features. By setting a first reference object, the first reference object is an object with a specific weight, namely, a first weight, and has a reference significance for sand and gravel measurement, such as sand and gravel per unit volume, and acquires the first image information. The acquisition feature information is the parameters in the process of acquiring the first image information, such as acquisition angle, acquisition pixels, acquisition distance, light environment, etc. The image of the first reference object is acquired according to the same acquisition feature information to ensure that the first image information The imaging effects of the third image information are similar, and the sand and gravel to be separated in the first image information can be accurately identified and quantitatively analyzed. By extracting image features of the first reference object with known weight and volume in the third image information, the second image feature is the image feature of the first reference object, and the corresponding calculation relationship between the first weight and the second image feature, that is, the first corresponding relationship, is obtained. The first image feature is the result of image feature extraction of the first image information. Based on the first corresponding relationship, that is, the mapping relationship between the image feature and the weight, the image features of the sand and gravel to be separated in the first image information are converted and analyzed to obtain the corresponding weight information of the sand and gravel to be separated in the first image feature, that is, the sand and gravel quantity information.

[0043] Step S300: input the sand and gravel amount information into the evaluation model to obtain water injection amount information;

[0044] Further, such as Figure 3 As shown, the sand and gravel amount information is input into the evaluation model to obtain the water injection amount information, and step S300 includes:

[0045] Step S310 constructs a neural network model;

[0046] Step S320: obtaining historical processing data, wherein the historical processing data includes information on the separation effect of the amount of sand and gravel processed and the amount of water injected;

[0047] Step S330: screening the analysis effect information according to preset requirements to obtain a screening processing data set, wherein the screening processing data set includes a processing sand and gravel volume and a water injection volume;

[0048] Step S340: obtaining model training data according to the screened and processed data set, training the neural network model through the model continuous data, and obtaining the evaluation model;

[0049] Step S350 obtains a second output result of the evaluation model, where the second output result includes the water injection volume information.

[0050] Specifically, the amount of water added is calculated according to the information of the amount of sand and gravel. Since the separation process requires the use of high-speed water flow to separate the sand and gravel, the amount of water for the sand and gravel to enter needs to be determined according to the state weight of the sand and gravel to be separated, so that the concentration of the sand and gravel mixed liquid obtained after adding water meets the separation requirements. The concentration of the sand and gravel mixed liquid has a certain influence on the separation effect. Too high or too low concentration is not conducive to separation. It is meaningful to keep it within a suitable concentration range to improve the separation effect. In order to improve the accuracy of force assessment, this application adds a neural network model, uses the historical data of previous operation separation to train the model, and uses the full concentration in the historical processing data The historical data of the foot separation effect is used as a training sample, and training data is randomly extracted from it to train the neural network model. The training process is essentially a supervised learning process. Each group of supervised data includes identification information of the amount of sand and gravel to be processed and the amount of water injection to be identified. The amount of sand and gravel to be processed is input into the neural network model. According to the identification information used to identify the amount of water injection, the neural network model continuously self-corrects and adjusts until the output result obtained is consistent with the identification information, then the supervised learning of this group of data is terminated and the supervised learning of the next group of data is carried out; when the output information of the neural network model reaches a predetermined accuracy rate / reaches a convergence state, the supervised learning process ends. Through supervised learning of the neural network model, the neural network model can process the input information more accurately, and the output water injection information can be more reasonable and accurate, so as to achieve the effect of accurately configuring the sand and gravel mixed liquid and improve the accuracy of the evaluation. The evaluation model is a trained and converged neural network model. Neural Networks (NN) is a complex neural network system formed by a large number of simple processing units (called neurons) that are widely connected to each other. It reflects many basic characteristics of human brain functions and is a highly complex nonlinear dynamic learning system. The neural network model is described based on the mathematical model of neurons. Artificial Neural Networks (ANN) is a description of the first-order characteristics of the human brain system. Simply put, it is a mathematical model. Through the training of a large amount of training data, the total amount of sand and gravel to be separated is input into the neural network model, and the matching water injection amount information is output, so as to realize the automatic evaluation of the water injection amount through computer machine learning, ensure that the mixed concentration of the sand and gravel mixture meets the separation effect, and effectively improve the operation efficiency and the reliability of the evaluation results by adding artificial intelligence technology, so as to avoid the errors caused by manual experience operation and affect the separation effect.

[0051] Step S400 obtains a torsion strength rule list, wherein the torsion strength rule list includes a correspondence between a sand-gravel mixture to be stirred, torsion strength, and separation results;

[0052] Specifically, the torsional strength rule list is a mapping relationship between torsional strength and sand-gravel mixture, torsional strength and separation results constructed according to historical data. It is data accumulated through practice and can ensure the reliability of the corresponding relationship. Different torsional strengths are set according to the weight and state of the sand-gravel mixture through the data relationship in the torsional strength rule list to obtain different separation results. Therefore, according to the torsional strength rule list, it is possible to achieve the matching of the corresponding torsional strength based on the requirements of the set separation results according to the weight of the sand-gravel mixture to be stirred.

[0053] Step S500: based on the torsional strength rule list, according to the water injection amount information and the sand and gravel amount information, obtain predicted torsional strength information;

[0054] Step S600 obtains a torsion control strategy based on the predicted torsion strength information, and controls the stirring speed of the sand and gravel separator according to the torsion control strategy.

[0055] Specifically, the weight and concentration information of the sand and gravel mixture to be separated are obtained according to the water injection information and the sand and gravel amount information. The corresponding separation result and torsional strength matching analysis are performed in the torsional strength rule list based on the obtained weight and concentration information of the sand and gravel mixture. After the separation result is ensured, the corresponding torsional strength can be obtained. If the separation result is certain, the corresponding torsional strength is determined according to the weight of the mixture to achieve the separation result. The torsional strength information is predicted, that is, the torsional strength matched with the mixed liquid information obtained according to the water injection information and the sand and gravel amount information. Different separation effects can be achieved by selecting different torsional strengths for sand and gravel mixtures with different weight and form requirements. Generally, a faster torsional speed will achieve a better separation effect, but too fast a torsional speed will cause energy consumption and equipment wear. How to balance the separation effect and equipment loss is the technical problem solved by the present application. The required torsional strength is calculated based on the weight of the liquid. The precise matching calculation of historical experimental data can avoid the influence of too low torsion on the separation effect and the equipment loss caused by too high torsion. The torsion control strategy includes setting the startup power of the sand and gravel separator, controlling the torsion speed and the torsion strength control during the entire separation process. For example, the startup speed is A, then accelerates to B and then remains stable. The set torsion control strategy is used to control the operation of the sand and gravel separator, and the corresponding separation control is achieved according to the specific state of the sand and gravel to be separated, which not only ensures the separation effect of sand and gravel, but also avoids unnecessary energy consumption and wear of the equipment. At the same time, the analysis and calculation process adds artificial intelligence technology to improve the calculation efficiency and result accuracy through machine learning, which solves the problem that the sand and gravel separator in the prior art operates according to a predetermined mode without considering the specific characteristics of the separated sand and gravel, and thus has the technical problem of poor sand and gravel separation effect and uncontrollable energy loss.

[0056] Further, such as Figure 4 As shown, the method includes:

[0057] Step S710: obtaining second image information through the image acquisition device, wherein the second image information includes characteristic information of the sand-gravel mixture;

[0058] Step S720: extracting features from the second image information to obtain feature information of the sand-gravel mixture;

[0059] Step S730: inputting the sand-gravel mixture characteristic information and the sand-gravel quantity information into a state evaluation model, wherein the state evaluation model is obtained through training convergence of multiple sets of training data, wherein each set of training data includes the sand-gravel mixture characteristic information, the sand-gravel quantity information, and identification information identifying the sand-gravel mixture concentration;

[0060] Step S740: obtaining a first output result of the state evaluation model, wherein the first output result includes a mixed state evaluation result, and the mixed state evaluation result is used to indicate the concentration of the sand-gravel mixed solution that matches the input sand-gravel mixed solution characteristic information and sand-gravel amount information;

[0061] Step S750 determines whether the mixed state evaluation result meets the first predetermined condition;

[0062] When the condition is not satisfied in step S760, the supplementary water injection amount information is obtained based on the mixed state evaluation result.

[0063] Specifically, during the sand and gravel separation process, the sand and gravel need to be stirred. For the sand and gravel mixture with high concentration, clean water needs to be added for stirring so that it is stirred evenly. Usually, how much water to inject and whether water injection is needed are manually judged, and its accuracy is inevitably affected by human factors. In the embodiment of the present application, the sand and gravel mixture is monitored in real time during the stirring process, and the stirred sand and gravel mixture is obtained by an image acquisition device. The second image information is the acquisition of the characteristics of the sand and gravel mixture during stirring. The image acquisition device is used to perform real-time image acquisition of the sand and gravel mixture during the stirring process, and the image information is used to extract the characteristic information of the sand and gravel mixture. The characteristic information of the sand and gravel mixture mainly reflects the concentration of the sand and gravel mixture, which is reflected by the mixing degree and fluidity parameters of the liquid. The characteristic information of the sand and gravel mixture and the sand and gravel amount information are comprehensively analyzed to determine whether the current mixture is stirred evenly and whether the concentration meets the requirements. If the concentration of the mixture is high, water injection is required. The amount of water injection is calculated according to the difference between the concentration and the requirement. The water pump is controlled to inject water according to the calculated amount of water injection to realize the automatic adjustment process of the concentration of the sand and gravel mixture, ensuring that the sand and gravel mixture is conducive to separation. Within the concentration range, in order to improve the accuracy of the mixed solution concentration evaluation results, the embodiment of the present application adds artificial intelligence technology, and analyzes and evaluates the concentration through machine deep learning. The state evaluation model is a neural network model through machine learning, and the training of the neural network model is converged using historical experimental data. The state evaluation model is obtained through training convergence through multiple sets of training data, and each set of training data includes sand and gravel mixed solution characteristic information, sand and gravel amount information, and identification information identifying the sand and gravel mixed concentration. The model learns that the sand and gravel mixed solution concentration evaluation algorithm is calculated and processed according to the input sand and gravel mixed solution characteristic information and sand and gravel amount information to obtain the sand and gravel mixed concentration information that matches it, that is, the mixed state evaluation result, which improves the calculation speed and calculation accuracy, and lays a solid foundation for accurate sand and gravel mixed solution concentration adjustment. When the mixed state evaluation result does not meet the first predetermined condition, the difference is calculated according to the mixed state evaluation result and the concentration value in the first predetermined condition, and the water injection amount is calculated according to the difference combined with the total amount of sand and gravel. The control operation of the water injection amount is performed according to the calculation result to ensure the concentration of the sand and gravel mixed solution, thereby ensuring the separation effect.

[0064] Furthermore, the method comprises:

[0065] Step S810: obtaining a first sensing force set and a second sensing force set through a gravity sensor, wherein the first sensing force set corresponds to a first position area, and the second sensing force set corresponds to a second position area;

[0066] Step S820: obtaining a first uniformity and a second uniformity according to the first sensing force set and the second sensing force set respectively;

[0067] Step S830: respectively judging whether the first uniformity and the second uniformity meet a second predetermined condition, and obtaining a judgment result;

[0068] Step S840 obtains an adjustment control strategy according to the judgment result.

[0069] Further, the control strategy is adjusted according to the judgment result, and step S840 includes:

[0070] Step S841: when the judgment result is the first result, the adjustment control strategy is to increase the stirring speed;

[0071] In step S842, when the judgment result is the second result, the adjustment control strategy is to maintain the stirring speed.

[0072] Specifically, the impact force of sand and gravel on the side wall during the mixing process is sensed and monitored by the gravity sensor arranged on the side wall of the separator. During the mixing and separation process, the rotating blades in the separator drive the lower sand and gravel mixture to rotate. The sand and gravel mixture will hit the side wall during the rotation process, thereby generating impact gravity. Since the separation of sand and gravel must be achieved during the mixing and rotating process, the sand and gravel will exist in different areas. As the separation process proceeds, the sensed impact force will gradually form a corresponding impact area. The first position area is the area where smaller particles of sand are rotated and hit, and the second position area is the area where larger particles of gravel are hit during the rotation process. The first sensing force set is the sum of the sensing forces for the areas where small particles of sand are hit. If the separation effect is good, the first sensing force set should be maintained within a uniform range. If the uniformity of the first sensing force set is poor, it indicates that the separation effect in the current area is uneven and there are different particle size ranges. When performing the first uniformity calculation, due to the differences in the particle morphology of the sand and the torque influence of the impact angle, there are differences. However, since they have common physical properties, the differences should be kept within a uniform range. Maintained within a certain range, so the reasonable range of sensing force should be considered when performing uniformity analysis, and data preprocessing is performed on the first sensing force set. The preprocessing can be a discreteness analysis of the first sensing force set, and the mean range of the data is obtained based on the discreteness analysis result, and the uniformity is calculated within the mean range. Similarly, the second sensing force set is the sum of the sensing forces collected in the second position area. Data analysis is performed on the second sensing force set to find the force range of the second position area, and the data in the second sensing force set that meets the force range is screened. The screened results are subjected to uniformity analysis. If the second uniformity meets the requirements, it indicates that the similarity of the particles in the area is high, otherwise it is low. If both the first uniformity and the second uniformity do not meet the requirements, and the overlapping range of the first sensing set and the second sensing set is large, it is judged that the current separation effect is not good, and the rotation speed needs to be increased to improve the separation effect. The first result is that the first uniformity and the second uniformity do not meet the second predetermined condition, wherein the first result includes multiple results such as the first uniformity and the second uniformity are not satisfied, one is satisfied, and / or the first sensing set and the second sensing set have a high degree of overlap. The second result is that the first uniformity and the second uniformity meet the second predetermined condition, which indicates that the current separation effect meets the requirements and no speed adjustment is required. The separation state is monitored in real time, and timely adjustments are made for separation effects that do not meet the requirements, avoiding rework due to poor separation and ensuring the technical effect of matching the separation machine operation parameter control with the separation effect.

[0073] Furthermore, the method comprises:

[0074] Step S910: obtaining device force information according to the first sensing force set and the second sensing force set;

[0075] Step S920: obtaining torsional strength information according to the torsion control strategy;

[0076] Step S930: input the equipment force information and torsional strength information into a loss prediction model;

[0077] Step S940 obtains a third output result of the loss prediction model, wherein the third output result includes a predicted loss result;

[0078] Step S950: When the predicted loss result exceeds the third preset condition, early warning information is obtained.

[0079] Specifically, in addition to the situation where the speed is insufficient to achieve the separation effect, there is also the situation where the speed is too fast and although the separation effect meets the requirements, there are energy consumption and wear of the equipment. In the case of the second result, that is, the first uniformity and the second uniformity both meet the requirements, the embodiment of the present application calculates the loss of the current equipment through the sensed gravity set combined with the torsional strength currently set in the torsional control strategy, and predicts the loss of the current equipment, such as the loss of the rotating impeller. The higher the speed, the greater the impact force of sand and gravel, which will cause the loss of the rotating impeller. The force information of the equipment, that is, the impact force sensed by the gravity sensor and the torsional strength information are analyzed and processed, and the impact force is calculated for the torsional strength information. According to the prediction, the predicted impact force is compared with the sensed force. If the sensed impact force is much greater than the predicted maximum impact force, it indicates that the current rotation speed is too large for the sand and gravel mixture being separated, or there are large particles in the sand and gravel mixture, which increase the sensed force and increase the wear of the equipment; if the difference between the predicted impact force and the sensed force is not large, it indicates that the requirements of the current operation separation are met and in line with expectations. The wear status is evaluated according to the exceeded impact force to obtain the predicted loss result, and it is determined whether the predicted loss result exceeds the preset requirements. If it exceeds the equipment loss requirements, an early warning is issued to remind that there is equipment wear in the current separator and corresponding adjustments need to be made. In order to improve the accuracy of the evaluation of the predicted loss results, the embodiment of the present application uses a neural network model for evaluation, calculates the centrifugal force based on the torsional strength information, and calculates the predicted force information based on the centrifugal force and the sand and gravel amount information; calculates the force difference based on the predicted force information and the equipment force information, and inputs the force difference and torsional strength information as input information into the loss prediction model. The loss prediction model is a neural network model in machine learning, which is obtained through training using multiple sets of training data. The multiple sets of training data all include force difference, torsional strength information, and identification information for identifying the loss results. The training process is essentially a supervised learning process. Each set of supervised data includes force difference, torsional strength information, and identification information for identifying the loss results. The force difference and torsional strength information are input into the neural network model. According to the identification information used to identify the loss results, the neural network model continuously corrects and adjusts itself until the output result obtained is consistent with the identification information, then the supervised learning of this set of data is terminated and the supervised learning of the next set of data is carried out; when the output information of the neural network model reaches a predetermined accuracy rate / reaches a convergence state, the supervised learning process ends. Through supervised learning of the neural network model, the neural network model can process the input information more accurately, and the output predicted loss results can be more reasonable and accurate, thereby achieving the technical effect of evaluating and warning of losses existing during the operation of the separator, and improving the calculation processing speed and the reliability of the prediction results.

[0080] Embodiment 2

[0081] Based on the same inventive concept as the monitoring and control method of a sand and gravel separator in the aforementioned embodiment, the present invention also provides a monitoring and control system for a sand and gravel separator, such as Figure 5 As shown, the system comprises:

[0082] A first obtaining unit 11, the first obtaining unit 11 is used to obtain first image information through an image acquisition device, the first image information including the total amount of sand and gravel to be separated;

[0083] A second obtaining unit 12, the second obtaining unit 12 is used to obtain sand and gravel amount information according to the first image information;

[0084] A third obtaining unit 13, the third obtaining unit 13 is used to input the sand and gravel amount information into an evaluation model to obtain water injection amount information;

[0085] A fourth obtaining unit 14, the fourth obtaining unit 14 is used to obtain a torsion strength rule list, the torsion strength rule list includes a correspondence between the sand-gravel mixture to be stirred, the torsion strength and the separation result;

[0086] A fifth obtaining unit 15, the fifth obtaining unit 15 is used to obtain predicted torsional strength information based on the torsional strength rule list, the water injection amount information, and the sand and gravel amount information;

[0087] The first execution unit 16 is used to obtain a torsion control strategy according to the predicted torsion strength information, and control the stirring speed of the sand and gravel separator according to the torsion control strategy.

[0088] Furthermore, the system further comprises:

[0089] a sixth obtaining unit, the sixth obtaining unit being used to obtain second image information through the image acquisition device, wherein the second image information includes characteristic information of the sand-gravel mixture;

[0090] a seventh obtaining unit, the seventh obtaining unit being used to extract features from the second image information to obtain feature information of the sand-gravel mixture;

[0091] A second execution unit, the second execution unit is used to input the sand-gravel mixture characteristic information and the sand-gravel amount information into a state evaluation model, wherein the state evaluation model is obtained through training convergence of multiple sets of training data, wherein each set of training data includes the sand-gravel mixture characteristic information, the sand-gravel amount information, and identification information identifying the sand-gravel mixture concentration;

[0092] An eighth obtaining unit, the eighth obtaining unit is used to obtain a first output result of the state evaluation model, the first output result includes a mixed state evaluation result, and the mixed state evaluation result is used to represent the concentration of the sand-gravel mixed solution that matches the input sand-gravel mixed solution characteristic information and sand-gravel amount information;

[0093] A first judgment unit, the first judgment unit is used to judge whether the mixed state evaluation result meets a first predetermined condition;

[0094] A ninth obtaining unit, wherein the ninth obtaining unit is used to obtain supplementary water injection amount information based on the mixed state evaluation result when it is not satisfied.

[0095] Furthermore, the system further comprises:

[0096] a third execution unit, the third execution unit being used to set a first reference object, wherein the first reference object has a first weight;

[0097] a tenth obtaining unit, configured to obtain acquisition feature information according to the first image information;

[0098] an eleventh obtaining unit, the eleventh obtaining unit being configured to perform image acquisition on the first reference object based on the acquisition feature information to obtain third image information;

[0099] a twelfth obtaining unit, the twelfth obtaining unit being used to respectively extract features from the first image information and the third image information to obtain first image features and second image features;

[0100] a thirteenth obtaining unit, configured to obtain a first corresponding relationship according to the first weight and the second image feature;

[0101] A fourteenth obtaining unit, the fourteenth obtaining unit is used to obtain the sand and gravel amount information based on the first corresponding relationship and according to the first image feature.

[0102] Furthermore, the system further comprises:

[0103] A first construction unit, wherein the first construction unit is used to construct a neural network model;

[0104] A fifteenth obtaining unit, the fifteenth obtaining unit is used to obtain historical processing data, the historical processing data including information on separation effect of processed sand and gravel volume and water injection volume;

[0105] a sixteenth obtaining unit, the sixteenth obtaining unit being used to screen the analysis effect information according to preset requirements to obtain a screening processing data set, the screening processing data set including a processing sand and gravel amount and a water injection amount;

[0106] A seventeenth obtaining unit, the seventeenth obtaining unit is used to obtain model training data according to the screening and processing data set, train the neural network model through the model continuous data, and obtain the evaluation model;

[0107] An eighteenth obtaining unit, the eighteenth obtaining unit is used to obtain a second output result of the evaluation model, wherein the second output result includes the water injection volume information.

[0108] Furthermore, the system further comprises:

[0109] A nineteenth obtaining unit, the nineteenth obtaining unit is used to obtain a first sensing force set and a second sensing force set through a gravity sensor, the first sensing force set corresponds to the first position area, and the second sensing force set corresponds to the second position area;

[0110] a twentieth obtaining unit, configured to obtain a first uniformity and a second uniformity according to the first induction force set and the second induction force set, respectively;

[0111] a second judging unit, the second judging unit being used to respectively judge whether the first uniformity and the second uniformity satisfy a second predetermined condition, and obtain a judging result;

[0112] A twenty-first obtaining unit, the twenty-first obtaining unit is used to obtain an adjustment control strategy according to the judgment result.

[0113] Furthermore, the system further comprises:

[0114] A fourth execution unit, wherein when the judgment result is the first result, the adjustment control strategy is to increase the stirring speed;

[0115] A fifth execution unit, wherein when the judgment result is the second result, the adjustment control strategy is to maintain the stirring speed.

[0116] Furthermore, the system further comprises:

[0117] a twenty-first obtaining unit, the twenty-first obtaining unit being configured to obtain device force information according to the first sensing force set and the second sensing force set;

[0118] a twenty-second obtaining unit, the twenty-second obtaining unit being configured to obtain torsional strength information according to the torsion control strategy;

[0119] A first input unit, the first input unit is used to input the force information and torsional strength information of the equipment into a loss prediction model;

[0120] a twenty-third obtaining unit, the twenty-third obtaining unit being used to obtain a third output result of the loss prediction model, wherein the third output result includes a predicted loss result;

[0121] The twenty-fourth obtaining unit is used to obtain early warning information when the predicted loss result exceeds a third preset condition.

[0122] The foregoing Figure 1 The various variations and specific examples of the monitoring and control method of a sand and gravel separator in Example 1 are also applicable to the monitoring and control system of a sand and gravel separator in this embodiment. Through the above detailed description of the monitoring and control method of a sand and gravel separator, those skilled in the art can clearly know the implementation method of the monitoring and control system of a sand and gravel separator in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0123] Exemplary Electronic Devices

[0124] Reference below Figure 6 To describe the electronic device of the embodiment of the present application.

[0125] Figure 6 The figure shows a schematic structural diagram of an electronic device according to an embodiment of the present application.

[0126] Based on the inventive concept of a monitoring and control method for a sand and gravel separator in the aforementioned embodiment, the present invention also provides a computer device on which a computer program is stored, which, when executed by a processor, implements the steps of any method of the monitoring and control method for a sand and gravel separator described above.

[0127] Among them, Figure 6 In the embodiment of the present invention, a bus architecture (represented by bus 300) is shown, which may include any number of interconnected buses and bridges, and bus 300 links together various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, namely a transceiver, which provides a unit for communicating with various other systems over a transmission medium.

[0128] The processor 302 is responsible for managing the bus 300 and general processing, while the memory 304 may be used to store data used by the processor 302 when performing operations.

[0129] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0130] A monitoring and control method for a sand and gravel separator provided in an embodiment of the present invention is applied to a monitoring and control system, the system comprising a monitoring and control device, the monitoring and control device comprising an image acquisition device, the method comprising: obtaining first image information through the image acquisition device, the first image information comprising the total amount of sand and gravel to be separated; obtaining sand and gravel amount information based on the first image information; inputting the sand and gravel amount information into an evaluation model to obtain water injection amount information; obtaining a torsional strength rule list, the torsional strength rule list comprising the correspondence between the sand and gravel mixture to be stirred, the torsional strength and the separation result; based on the torsional strength rule list, obtaining predicted torsional strength information according to the water injection amount information and the sand and gravel amount information; obtaining a torsional control strategy based on the predicted torsional strength information, and controlling the stirring speed of the sand and gravel separator according to the torsional control strategy. The corresponding separation control is achieved according to the specific state of the sand and gravel to be separated, which not only ensures the separation effect of sand and gravel, but also avoids unnecessary energy consumption and wear of the equipment. At the same time, artificial intelligence technology is added to the analysis and calculation process to improve the calculation efficiency and result accuracy through machine learning, thereby solving the technical problem that the sand and gravel separator in the prior art operates according to a predetermined mode without considering the specific characteristics of the separated sand and gravel, resulting in poor sand and gravel separation effect and uncontrollable energy loss.

[0131] Those of ordinary skill in the art will appreciate that the various digital numbers such as the first and second involved in the present application are only for the convenience of description, and are not used to limit the scope of the embodiments of the present application, nor do they represent the order of precedence. "And / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one" refers to one or more. At least two refers to two or more. "At least one", "any one" or similar expressions refer to any combination of these items, including any combination of single items (individuals) or plural items (individuals). For example, at least one item (individual, kind) of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0132] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions

[0133] The instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium, an optical medium, or a semiconductor medium, etc.

[0134] The various illustrative logic units and circuits described in the embodiments of the present application can be implemented or operated by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or the design of any combination of the above functions. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any traditional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of computing devices, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration to implement.

[0135] The steps of the method or algorithm described in the embodiments of the present application can be directly embedded in hardware, a software unit executed by a processor, or a combination of the two. The software unit can be stored in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD ROM, or any other form of storage medium in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC, and the ASIC can be arranged in a terminal. Optionally, the processor and the storage medium can also be arranged in different components in the terminal. These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0136] Although the present application has been described in conjunction with specific features and embodiments thereof, it will be apparent that various modifications and combinations thereof can be made without departing from the spirit and scope of the present application.

[0137] Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include these modifications and variations.

Claims

1. A monitoring and control method for a sand and gravel separator, wherein: The method is applied to a monitoring and control system, the system includes a monitoring and control device, the monitoring and control device includes an image acquisition device, and the method includes: Obtaining first image information by an image acquisition device, wherein the first image information includes the total amount of sand and gravel to be separated; According to the first image information, obtaining sand and gravel amount information; Inputting the sand and gravel quantity information into an evaluation model to obtain water injection quantity information; Obtaining a torsional strength rule list, wherein the torsional strength rule list includes a correspondence between a sand-gravel mixture to be stirred, torsional strength, and a separation result; Based on the torsional strength rule list, and according to the water injection amount information and the sand and gravel amount information, the predicted torsional strength information is obtained; According to the predicted torsion strength information, a torsion control strategy is obtained, and the stirring speed of the sand and gravel separator is controlled according to the torsion control strategy; The method comprises: Obtaining second image information through the image acquisition device, wherein the second image information includes characteristic information of the sand-gravel mixture; Performing feature extraction on the second image information to obtain feature information of the sand-gravel mixture; Inputting the characteristic information of the sand-gravel mixture and the sand-gravel quantity information into a state evaluation model, wherein the state evaluation model is obtained through training convergence of multiple sets of training data, wherein each set of training data includes the characteristic information of the sand-gravel mixture, the sand-gravel quantity information, and identification information identifying the sand-gravel mixture concentration; Obtaining a first output result of the state evaluation model, wherein the first output result includes a mixed state evaluation result, and the mixed state evaluation result is used to represent the concentration of the sand-gravel mixed solution that matches the input sand-gravel mixed solution characteristic information and sand-gravel amount information; Determining whether the mixed state evaluation result meets a first predetermined condition; When the condition is not satisfied, obtaining supplementary water injection amount information based on the mixed state evaluation result; The step of inputting the sand and gravel quantity information into an evaluation model to obtain water injection quantity information includes: Build a neural network model; Obtaining historical processing data, wherein the historical processing data includes information on the separation effect of the amount of sand and gravel processed and the amount of water injected; The separation effect information is screened according to preset requirements to obtain a screened processing data set, wherein the screened processing data set includes a processed sand and gravel volume and a water injection volume; Obtaining model training data according to the screened and processed data set, training the neural network model through the model continuous data, and obtaining the evaluation model; A second output result of the evaluation model is obtained, wherein the second output result includes the water injection volume information.

2. The method of claim 1, wherein: The step of obtaining sand and gravel quantity information according to the first image information includes: Setting a first reference object, wherein the first reference object has a first weight; Obtaining acquisition feature information according to the first image information; Based on the acquisition feature information, perform image acquisition on the first reference object to obtain third image information; Extracting features from the first image information and the third image information respectively to obtain first image features and second image features; Obtaining a first corresponding relationship according to the first weight and the second image feature; Based on the first corresponding relationship and according to the first image feature, the sand and gravel amount information is obtained.

3. The method of claim 1, wherein: The monitoring and control device further includes a gravity sensor, and the method includes: Obtaining a first sensing force set and a second sensing force set through a gravity sensor, wherein the first sensing force set corresponds to a first position area, and the second sensing force set corresponds to a second position area; Obtaining a first uniformity and a second uniformity according to the first induction force set and the second induction force set respectively; respectively determining whether the first uniformity and the second uniformity meet a second predetermined condition, and obtaining a determination result; According to the judgment result, an adjustment control strategy is obtained.

4. The method of claim 3, wherein: The step of obtaining an adjustment control strategy according to the judgment result includes: When the judgment result is the first result, the adjustment control strategy is to increase the stirring speed; When the judgment result is the second result, the adjustment control strategy is to maintain the stirring speed.

5. The method of claim 3, wherein: The method comprises: Obtaining device force information according to the first sensing force set and the second sensing force set; According to the torsion control strategy, obtaining torsion strength information; Inputting the force information and torsional strength information of the equipment into a loss prediction model; Obtaining a third output result of the loss prediction model, wherein the third output result includes a predicted loss result; When the predicted loss result exceeds a third preset condition, early warning information is obtained.

6. A monitoring and control system for a sand and gravel separator, wherein: The system is applied to the method according to any one of claims 1 to 5, and the system comprises: A first obtaining unit, the first obtaining unit is used to obtain first image information through an image acquisition device, wherein the first image information includes the total amount of sand and gravel to be separated; a second obtaining unit, the second obtaining unit being used to obtain sand and gravel amount information according to the first image information; a third obtaining unit, the third obtaining unit being used to input the sand and gravel amount information into an evaluation model to obtain water injection amount information; A fourth obtaining unit, the fourth obtaining unit is used to obtain a torsion strength rule list, the torsion strength rule list including a correspondence between a sand-gravel mixture to be stirred, torsion strength, and a separation result; a fifth obtaining unit, the fifth obtaining unit being used to obtain predicted torsional strength information based on the torsional strength rule list, according to the water injection amount information and the sand and gravel amount information; The first execution unit is used to obtain a torsion control strategy according to the predicted torsion strength information, and control the stirring speed of the sand and gravel separator according to the torsion control strategy.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

Images