Ultrasonic anti-blocking re-mixing water and fertilizer machine device

Abstract

The application relates to the technical field of agricultural machinery, and discloses an ultrasonic anti-blocking and re-mixing water and fertilizer machine device, which comprises a water and fertilizer machine pipeline and a fixing component, the fixing component comprises a transducer fixing component and a sensor fixing component, the transducer fixing component is used for fixing an ultrasonic module on the water and fertilizer machine pipeline, and a vibration sensor is fixed on the water and fertilizer machine pipeline through the sensor fixing component at two ends of the transducer fixing component. The ultrasonic anti-blocking and re-mixing water and fertilizer machine device further comprises a monitoring module, the monitoring module is connected with the ultrasonic module and the vibration sensor, convolution neural training data are obtained by adjusting parameters, a neural network is obtained by dimension reduction through pooling, then the classification of vibration waveforms is intelligently identified, the working condition parameters of the ultrasonic module can be adjusted through the classification of the vibration waveforms, optimal cleaning working condition parameters are intelligently adjusted, the fertilization efficiency is stabilized, and the utilization rate of fertilizers is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of agricultural machinery, in particular to an ultrasonic anti-blocking and re-mixing water and fertilizer machine device. BACKGROUND

[0002] The long-term use of the water and fertilizer machine will cause many algae to grow in the pipeline due to the rich nutrients, and the inner wall of the pipeline will be mixed with a large amount of scale or fertilizer impurities. The large accumulation of fertilizer in the pipeline will cause the water and fertilizer machine to be blocked, which not only affects the normal work of the water and fertilizer machine, but also reduces the utilization efficiency of the fertilizer and the uniformity of the water and fertilizer mixture, ultimately affecting the growth of crops. The traditional cleaning and dredging of the water and fertilizer machine requires disassembly and even replacement of related parts of the water and fertilizer machine, which is not only low in efficiency but also complex in cleaning method. Convolutional neural network is a deep network that simulates the visual cortex of the brain for image recognition and processing, which can be effectively used in vibration signal recognition. Therefore, the design of an ultrasonic anti-blocking and re-mixing water and fertilizer machine device can prevent the water and fertilizer machine from being blocked and achieve the effect of secondary mixing of water and fertilizer, improve the efficiency of algae removal and prevent blockage, improve the stability of fertilization, and ensure the yield of crops. SUMMARY

[0003] In order to overcome the above-mentioned shortcomings, the present application provides an ultrasonic anti-blocking and re-mixing water and fertilizer machine device, which combines the cavitation effect of ultrasonic waves with an intelligent water and fertilizer machine to solve the above-mentioned problems.

[0004] The present application provides the following technical solutions:

[0005] An ultrasonic anti-blocking and re-mixing water and fertilizer machine device, comprising a water and fertilizer machine pipeline fixing component, further comprising a fixing component, a vibration sensor, an ultrasonic module and a monitoring module; the fixing component comprises a transducer fixing component and a sensor fixing component, the ultrasonic transducer fixing component fixes the ultrasonic module on the water and fertilizer machine pipeline, vibration sensors are arranged on both sides of the ultrasonic module, the vibration sensors are fixed on the water and fertilizer machine pipeline through the sensor fixing component, and the monitoring module is connected with the ultrasonic module and the vibration sensors.

[0006] In the preferred technical solution of the present application, the ultrasonic module comprises an ultrasonic wave emitting device and an ultrasonic transducer, the ultrasonic wave emitting device is connected with the ultrasonic transducer, and the ultrasonic transducer fixing component fixes the ultrasonic transducer on the water and fertilizer machine pipeline.

[0007] In the preferred technical solution of the present application, the ultrasonic transducer contains two or more array elements.

[0008] In the preferred technical solution of the present application, the monitoring module is connected with the ultrasonic wave emitting device.

[0009] In the preferable technical scheme of the present application, the monitoring module comprises a signal processing module, a data storage module and a display module, and the data storage module and the display module are electrically connected with the signal processing module.

[0010] In the preferable technical scheme of the present application, at least two vibration sensors are connected to the signal processing module of the monitoring module.

[0011] In the preferable technical scheme of the present application, the data storage module stores the vibration waveform data collected by the vibration sensors and the convolution neural training sample data when the ultrasonic wave emitting device is in working condition.

[0012] In the preferable technical scheme of the present application, the initial input layer data is obtained by adjusting the ultrasonic time, the ultrasonic wave emitting device power, the ultrasonic wave frequency, the ultrasonic anti-blocking and re-mixing water and fertilizer machine device use time, the water and fertilizer liquid concentration, the fertilizer type and the type of the blocking object, the convolution neural network is obtained through pooling dimension reduction, and the vibration waveform data of the convolution neural training sample data is obtained.

[0013] In the preferable technical scheme of the present application, when the ultrasonic wave emitting device is in working condition, a specific ultrasonic wave emitting device power, an ultrasonic wave frequency, an ultrasonic anti-blocking and re-mixing water and fertilizer machine device use time, a water and fertilizer liquid concentration, a fertilizer type and one parameter value and one parameter type of the convolution neural training sample data are given, N vibration sensors collect the to-be-identified vibration waveform data, the trained convolution neural network is input, the type classification information of the blocking object corresponding to the vibration waveform data is identified, and the working condition parameters of the ultrasonic wave emitting device are optimized and adjusted.

[0014] The optimized and adjusted working condition parameters of the ultrasonic wave emitting device are input again into the convolution neural training sample data in the data storage module as input layer data, the convolution neural network is repeatedly adjusted through pooling dimension reduction.

[0015] The data storage module stores the vibration waveform data collected by N vibration sensors and the convolution neural training sample data when the ultrasonic wave emitting device is in working condition.

[0016] The initial input layer data is obtained by adjusting the ultrasonic time, the ultrasonic wave emitting device power, the ultrasonic wave frequency, the use time of the ultrasonic anti-blocking re-mixing water and fertilizer machine device, the water and fertilizer liquid concentration, the fertilizer type and the type of the blocking object, the parameters in the convolutional neural network are trained using the error back propagation algorithm, the convolutional neural network is obtained, and the vibration waveform data of the convolutional neural training sample data is obtained. In the reverse error calculation, the convolutional layer is rewritten as a fully connected layer, and the pooling layer is rewritten as a partially connected fully connected layer. The weight adjustment of the convolution kernel is adjusted layer by layer from the connection weight of the uppermost layer, and the cross-entropy cost function is used as the error function. The units in each pooling region are connected to the units obtained after pooling, the pooling layer is changed to a partially connected fully connected layer, the error is propagated between each unit connected thereto, and the weight of each connection is determined.

[0017] When the ultrasonic wave emitting device is in working condition, a specific parameter value and a parameter type of the ultrasonic wave emitting device power, the ultrasonic wave frequency, the use time of the ultrasonic anti-blocking re-mixing water and fertilizer machine device, the water and fertilizer liquid concentration and the fertilizer type of the convolutional neural training sample data are given, N vibration sensors collect the vibration waveform data to be identified, input the trained convolutional neural network, identify the blocking object type classification information corresponding to the vibration waveform data, and then optimize and adjust the working condition parameters of the ultrasonic wave emitting device.

[0018] Preferably, adjusting the working condition parameters of the ultrasonic wave emitting device includes the ultrasonic wave emitting device power, the ultrasonic wave frequency and the ultrasonic time.

[0019] Preferably, the working condition parameters of the ultrasonic wave emitting device that have been optimized and adjusted are input again as input layer data in the convolutional neural training sample data in the data storage module, the dimensionality reduction of pooling is repeated, the convolutional neural network is adjusted, and supervised feature learning in deep learning is realized.

[0020] The ultrasonic anti-blocking re-mixing water and fertilizer machine device provided by the application has the following advantages:

[0021] (1) The cavitation effect of ultrasonic waves is combined with an intelligent water and fertilizer machine, and the power and frequency of the ultrasonic waves emitted when the cleaning effect is best are debugged, so that the effect of non-contact cleaning and dredging the water and fertilizer machine can be achieved, and the labor cost is saved.

[0022] (2) The water and fertilizer machine is cleaned and dredged in multiple directions through the detachability of the transducer fixing part, the efficiency and effect of preventing blocking are improved, and the stability of fertilization is improved.

[0023] (3) In the working of the ultrasonic emission device, the ultrasonic waves will produce cavitation effect in the water and fertilizer liquid, refine the larger fertilizer particles in the water and fertilizer liquid, deepen the mixing degree of the fertilizer in the water, and finally realize the effect of secondary mixing of water and fertilizer, and improve the utilization rate of the fertilizer;

[0024] (4) The cleaning effect is monitored through the vibration sensor, the cleaning effect of the ultrasonic wave on the water and fertilizer machine can be effectively monitored, the starting frequency and time of the equipment are determined, the consumption of electric energy is saved, the water and fertilizer machine is designed with the fertilization irrigation mode of clean water-water fertilizer-clean water, and the anti-blocking effect of the water and fertilizer machine is best. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 It is the ultrasonic module and sensor module overhead structure diagram of the ultrasonic anti-blocking re-mixed water and fertilizer machine device of the application;

[0026] Figure 2 It is the left view structure diagram of the ultrasonic module and sensor module of the ultrasonic anti-blocking re-mixed water and fertilizer machine device of the application;

[0027] Figure 3 It is the module composition structure schematic diagram of the ultrasonic anti-blocking re-mixed water and fertilizer machine device of the application;

[0028] Figure 4 It is the vibration waveform schematic diagram collected by the sensor module under different parameter conditions of the application;

[0029] Figure 5 It is the training sample and the comparison of the pooled full connection vibration waveform of the application.

[0030] In the figure: 1 is an ultrasonic transducer, 2 is a vibration sensor, 3 is a sensor fixing part, 4 is a transducer fixing part, 6 is a water and fertilizer machine pipeline, 8 is an ultrasonic wave emission device; 91 is the data characteristics of metal blockage, 92 is the data characteristics of algae blockage, 10 is a sensor lead, 11 is an ultrasonic transducer lead. DETAILED DESCRIPTION

[0031] It should be noted that the embodiments in the application and the features in the embodiments can be combined with each other without conflict. The application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0032] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. The description of the at least one example embodiment is actually only illustrative, but not as any limitation on the present application and its application or use. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0033] Embodiment

[0034] The ultrasonic anti-blocking re-mixed water and fertilizer machine device provided by the embodiment comprises a water and fertilizer machine pipeline 6, a fixing component, a vibration sensor 2, an ultrasonic module and a monitoring module. The fixing component comprises a transducer fixing component 4 and a sensor fixing component 3. The ultrasonic transducer 1 fixing component fixes the ultrasonic module on the water and fertilizer machine pipeline 6. The vibration sensor 2 is arranged on both sides of the ultrasonic module and is fixed on the water and fertilizer machine pipeline 6 through the sensor fixing component 3. The monitoring module is connected to the ultrasonic module and the vibration sensor 2.

[0035] The water and fertilizer machine pipeline 6 is laid along the water and fertilizer machine and the water and fertilizer supply component. The water and fertilizer machine pipeline 6 is responsible for conveying water and fertilizer nutrients to the water and fertilizer machine. During the conveying of water and fertilizer, water and fertilizer is prone to accumulate in the pipeline, thereby causing pipeline blockage. In order to detect the position of the pipeline where the blockage occurs in time and then clean it, the pipeline can quickly recover to an unblocked state. When a certain section of the pipeline is blocked, the ultrasonic module emits ultrasonic waves. The ultrasonic waves are transmitted to the blocked position through the water and fertilizer liquid, and the water and fertilizer nutrients squeezed by the ultrasonic waves are dispersed. In the process of ultrasonic cleaning, the vibration sensor 2 detects the cleaning effect and can determine the starting frequency and time of the equipment. The ultrasonic waves also produce cavitation effect in the water and fertilizer liquid, so that larger particles in the water and fertilizer liquid can be refined, the mixing degree of the fertilizer in the water is deepened, the secondary mixing of the water and fertilizer is realized, and the utilization efficiency of the fertilizer is improved. That is, the pipeline can be quickly unblocked, and the effect of the fertilizer can be enhanced.

[0036] Further, the ultrasonic module comprises an ultrasonic emitter 8 and an ultrasonic transducer 1. The ultrasonic emitter 8 is connected to the ultrasonic transducer 1. The ultrasonic transducer 1 fixing component fixes the ultrasonic transducer 1 on the water and fertilizer machine pipeline 6. The ultrasonic emitter provides ultrasonic energy for the ultrasonic transducer 1. The ultrasonic transducer 1 is attached to the pipeline, and the ultrasonic energy is transmitted to the inside of the pipeline through contact.

[0037] Further, the ultrasonic transducer 1 contains two or more than two array elements.

[0038] Further, the monitoring module is connected with the ultrasonic wave emitting device 8.

[0039] Further, the monitoring module comprises a signal processing module, a data storage module and a display module, and the data storage module and the display module are electrically connected with the signal processing module. The signal processing module is responsible for receiving the electrical signals transmitted by each sensor, processing the electrical signals, storing the signal information in the data storage module and displaying the signal information through the display module.

[0040] Further, at least two vibration sensors 2 are connected to the signal processing module of the monitoring module.

[0041] Further, the data storage module stores the vibration waveform data collected by the vibration sensor 2 and the convolutional neural training sample data when the ultrasonic wave emitting device 8 is in working condition.

[0042] Further, the initial input layer data is obtained by adjusting the ultrasonic time, the power of the ultrasonic wave emitting device 8, the ultrasonic wave frequency, the use time of the ultrasonic anti-blocking re-mixed water and fertilizer machine device, the concentration of the water and fertilizer liquid, the type of fertilizer and the type of blocking object, the convolutional neural network is obtained by pooling and dimension reduction, and the vibration waveform data of the convolutional neural training sample data is obtained.

[0043] Further, when the ultrasonic wave emitting device 8 is in working condition, a specific power of the ultrasonic wave emitting device 8, an ultrasonic wave frequency, a use time of the ultrasonic anti-blocking re-mixed water and fertilizer machine device, a concentration of the water and fertilizer liquid, a type of fertilizer and one parameter value and one parameter type of the convolutional neural training sample data are given, N vibration sensors 2 collect the vibration waveform data to be identified, input the trained convolutional neural network, identify the classification information of the type of blocking object corresponding to the vibration waveform data, and then optimize and adjust the working condition parameters of the ultrasonic wave emitting device 8.

[0044] The optimized and adjusted working condition parameters of the ultrasonic wave emitting device 8 are input again into the convolutional neural training sample data in the data storage module as input layer data, and the convolutional neural network is adjusted by repeating pooling and dimension reduction.

[0045] The working principle of the monitoring module is as follows:

[0046] The data storage module stores the vibration waveform data collected by N vibration sensors 2 and the convolutional neural training sample data when the ultrasonic wave emitting device 8 is in working condition.

[0047] The initial input layer data is obtained by adjusting the ultrasonic time, the power of the ultrasonic wave emitting device 8, the ultrasonic wave frequency, the use time of the ultrasonic anti-blocking re-mixing water and fertilizer machine device, the water and fertilizer liquid concentration, the fertilizer type and the type of the blocking object, the parameters in the convolutional neural network are trained using the error back propagation algorithm, the convolutional neural network is obtained, and the vibration waveform data of the convolutional neural training sample data is obtained, as shown in Figure 4 In the reverse error calculation, the convolutional layer is rewritten as a fully connected layer, and the pooling layer is rewritten as a partially connected fully connected layer. The weight adjustment of the convolution kernel is adjusted layer by layer from the connection weight of the uppermost layer, and the cross-entropy cost function is used as the error function. Each unit in each pooling region is connected to the unit obtained after pooling, the pooling layer is changed to a partially connected fully connected layer, and the error is propagated between each unit connected thereto to determine the weight of each connection.

[0048] As shown in Figure 5 When the ultrasonic wave emitting device 8 is in working condition, a specific parameter value and a parameter type of the power of the ultrasonic wave emitting device 8, the ultrasonic wave frequency, the use time of the ultrasonic anti-blocking re-mixing water and fertilizer machine device, the water and fertilizer liquid concentration and the fertilizer type of the convolutional neural training sample data are given, N vibration sensors 2 collect the to-be-identified vibration waveform data, input the trained convolutional neural network, identify the blocking object type classification information corresponding to the vibration waveform data, and then optimize and adjust the working condition parameters of the ultrasonic wave emitting device 8.

[0049] The working condition parameters of the ultrasonic wave emitting device 8 include the power of the ultrasonic wave emitting device 8, the ultrasonic wave frequency and the ultrasonic time.

[0050] The optimized and adjusted working condition parameters of the ultrasonic wave emitting device 8 are input again into the convolutional neural training sample data in the data storage module as input layer data, the dimensionality reduction of the repeated pooling is optimized, the convolutional neural network is optimized, and the supervised feature learning in deep learning is realized.

[0051] In some embodiments, the water and fertilizer machine adopts a water-fertilizer-water mode of fertilization irrigation.

[0052] The working principle of the ultrasonic anti-blocking re-mixing water and fertilizer machine device of the application is as follows:

[0053] In operation, the ultrasonic anti-blocking and remixing device mainly converts the acoustic energy of the power ultrasonic frequency source in the ultrasonic emission device 8 into mechanical vibration through the ultrasonic transducer 1 fixed to the transducer fixing member 4, and radiates ultrasonic waves to the water-fertilizer liquid in the water-fertilizer machine pipeline 6 through the transducer fixing member 4. Due to the radiation of ultrasonic waves, the micro-bubbles in the water-fertilizer liquid in the water-fertilizer machine pipeline 6 can vibrate under the action of the sound waves. The cavitation effect of the ultrasonic waves not only causes the fatigue failure of the adsorbed dirt layer on the inner surface of the water-fertilizer machine pipeline 6 to be removed, but also causes the fertilizers to be refined and the mixing degree of the fertilizers in water to be deepened, achieving the effect of secondary mixing. Due to the peeling of the dirt and the refinement of the fertilizers in water, the effect of preventing blockage is achieved. The transducer fixing member (4) and the sensor fixing member 3 are fixedly connected by bolts and nuts. In operation, the vibration sensor 2 collects the vibration waveform of the water-fertilizer machine pipeline 6, the data processing module (not shown in the figure) analyzes the vibration signal through the trained convolutional neural network, the data storage module (not shown in the figure) stores the related vibration data, and finally the display module displays the display time and the cleaning effect. When the cleaning effect is good, the ultrasonic anti-blocking and remixing device is turned off.

[0054] The technical beneficial effects obtained by the present application are: 1) the power and frequency of the emitted ultrasonic waves when the cleaning effect reaches the best are debugged, which can achieve the effect of non-contact cleaning and dredging of the water-fertilizer machine; 2) the detachability of the transducer fixing member (4) can clean and dredge the water-fertilizer machine in multiple directions, improving the efficiency and effect of preventing blockage; 3) when the ultrasonic emission device is working, the ultrasonic waves will produce cavitation effect in the water-fertilizer liquid, refine the larger fertilizer particles in the water-fertilizer liquid, and deepen the mixing degree of the fertilizers in water, finally realizing the secondary mixing of water and fertilizer; 4) the cleaning effect is monitored by the vibration sensor (2), which can effectively monitor the cleaning effect of the ultrasonic waves on the water-fertilizer machine, and determine the starting frequency and time of the equipment, saving the consumption of electric energy.

[0055] The technical features of the above-described embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described, but as long as the combinations of the technical features do not exist, they should be considered as within the scope of the present application.

[0056] The above-described embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled persons in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the protection scope of the present application. The protection scope of the present application should be subject to the appended claims.

Claims

1. An ultrasonic anti-blocking re-mixing water and fertilizer machine device, characterized in that: it comprises a water and fertilizer machine pipeline (6), and further comprises a fixing component, a vibration sensor (2), an ultrasonic module and a monitoring module; the fixing component comprises a transducer fixing component (4) and a sensor fixing component (3), the transducer fixing component (4) fixes the ultrasonic module on the water and fertilizer machine pipeline (6), vibration sensors (2) are arranged on both sides of the ultrasonic module, and the vibration sensors (2) are fixed on the water and fertilizer machine pipeline (6) through the sensor fixing component (3); the monitoring module is connected with the ultrasonic module and the vibration sensors (2); the ultrasonic module comprises an ultrasonic emission device (8) and an ultrasonic transducer (1), the ultrasonic emission device (8) is connected with the ultrasonic transducer (1), and an ultrasonic transducer (1) fixing component fixes the ultrasonic transducer (1) on the water and fertilizer machine pipeline (6); the ultrasonic transducer (1) contains more than two array elements; the monitoring module is connected with the ultrasonic emission device (8); the monitoring module comprises a signal processing module, a data storage module and a display module, and the data storage module and the display module are electrically connected with the signal processing module; at least two vibration sensors (2) are connected to the signal processing module of the monitoring module; the data storage module stores vibration waveform data and convolutional neural training sample data collected by the vibration sensors (2) when the ultrasonic emission device (8) is in a working condition; initial input layer data is obtained by adjusting ultrasonic time, ultrasonic emission device (8) power, ultrasonic frequency, ultrasonic anti-blocking re-mixing water and fertilizer machine device use time, water and fertilizer liquid concentration, fertilizer type and blockage type, dimensionality reduction is performed through pooling to obtain a convolutional neural network, and the vibration waveform data of the convolutional neural training sample data is obtained; when the ultrasonic emission device (8) is in a working condition, a specific ultrasonic emission device (8) power, ultrasonic frequency, ultrasonic anti-blocking re-mixing water and fertilizer machine device use time, water and fertilizer liquid concentration, fertilizer type and one parameter value and one parameter type of the convolutional neural training sample data are given, N vibration sensors (2) collect to-be-identified vibration waveform data, the convolutional neural network obtained by training is input, the blockage type classification information corresponding to the vibration waveform data is identified, and the working condition parameters of the ultrasonic emission device (8) are optimized and adjusted; the working condition parameters of the ultrasonic emission device (8) that have been optimized and adjusted are input again into the convolutional neural training sample data in the data storage module as input layer data, dimensionality reduction is repeatedly performed through pooling, and the convolutional neural network is adjusted. ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​

Images