A method and system for controlling the jacking speed of a micro pipe jacking machine

Abstract

The present invention relates to the field of mechanical control, and in particular to a method and system for controlling the jacking speed of a micro pipe jacking machine. The method comprises: collecting first data and second data, wherein the first data is the load, system pressure, and hydraulic pump power of the micro pipe jacking machine at the current moment, and the second data is the jacking speed error and speed error change rate of the micro pipe jacking machine at the current moment; predicting the third data of the micro pipe jacking machine according to the first data and a pre-trained neural network model; combining the second data and the third data, using a fuzzy proportional-integral-differential controller to obtain fourth data, and controlling the jacking speed of the micro pipe jacking machine according to the fourth data. The present invention effectively solves the problem of failure caused by the non-intelligent adjustment of the jacking speed of the micro pipe jacking machine in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of mechanical control, and more specifically, to a method and system for controlling the jacking speed of a micro pipe jacking machine. Background Art

[0002] In recent years, with the comprehensive and rapid development of science and technology, the construction of urban subways has also shown rapid development. Due to the increasing density of cities and the continuous increase of high-rise buildings on the ground, the available space on the ground is shrinking rapidly. Therefore, considering the utilization of underground space has become a top priority and is also the primary task of the current rapid urban development.

[0003] In underground space construction, micro pipe jacking machines can complete the construction and maintenance of stations and tunnels in places where construction is difficult underground; in mining work, micro pipe jacking machines can be used to support the stability of the well wall and lay pipelines, cables and other facilities. The micro pipe jacking machine is mainly composed of a rotary excavation system, a main top hydraulic propulsion system, a soil conveying system, a grouting system, a measuring device, a ground hoisting device and an electrical system. The control of its jacking speed is the control of the hydraulic system of the micro pipe jacking machine.

[0004] However, the traditional micro pipe jacking machine control system does not take into account the complex internal and external influences, and the jacking speed control of the pipe jacking machine is only set and executed by a single control unit. When the external environment changes, the pipe jacking machine cannot adjust the jacking speed in time, which may cause the pipe jacking machine to overload, and in severe cases, it may cause the pipe jacking machine to malfunction, greatly affecting construction safety and project progress. Summary of the invention

[0005] In order to solve the problem in the prior art that the micro pipe jacking machine's jacking speed adjustment is not intelligent and causes the pipe jacking machine to malfunction, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a method for controlling the jacking speed of a micro pipe jacking machine, comprising: collecting first data and second data, wherein the first data is the load, system pressure, and hydraulic pump power of the micro pipe jacking machine at the current moment, and the second data is the jacking speed error and the speed error change rate of the micro pipe jacking machine at the current moment; predicting third data of the micro pipe jacking machine based on the first data and a pre-trained neural network model; combining the second data and the third data, obtaining fourth data using a fuzzy proportional-integral-differential controller, and controlling the jacking speed of the micro pipe jacking machine based on the fourth data.

[0007] The above scheme combines a neural network with a fuzzy controller. The neural network can timely predict the third data of the micro pipe jacking machine, and then combine the predicted third data with the collected second data and input them into the proportional-integral-differential controller. The micro pipe jacking machine can be timely controlled to adjust the jacking speed at the next moment, no longer relying on manual or simple controllers. The neural network can realize intelligent control of the jacking speed, thereby solving the problem of failure caused by the unintelligent adjustment of the jacking speed of the micro pipe jacking machine in the prior art.

[0008] Preferably, the third data is the load, system pressure and hydraulic pump power of the micro pipe jacking machine at the next moment; the fourth data is the proportion, integral and differential coefficient of the jacking speed error of the micro pipe jacking machine.

[0009] Preferably, the pre-trained neural network model includes: collecting fifth data, wherein the fifth data is the micro pipe jacking machine load, system pressure, hydraulic pump power at multiple previous moments and the corresponding micro pipe jacking machine load, system pressure, hydraulic pump power at the next moment; preprocessing the fifth data to obtain sixth data; and using the sixth data to train a convolutional neural network to obtain a neural network model.

[0010] The above scheme trains the neural network model, which can efficiently and accurately predict the micro pipe jacking machine load, system pressure, and hydraulic pump power at the next moment.

[0011] Preferably, preprocessing the fifth data includes: correcting abnormal data in the fifth data; and denoising the fifth data using wavelet transform.

[0012] The above scheme can reduce the impact of abnormal data or noise data on the entire neural network model by correcting and denoising the data.

[0013] Preferably, the second data and the third data are combined, a fuzzy proportional-integral-differential controller is used to obtain fourth data, and the jacking speed of the micro pipe jacking machine is controlled according to the fourth data, including: fuzzifying, fuzzy reasoning and defuzzifying the second data to obtain a first proportional coefficient, a first integral coefficient and a first differential coefficient; combining the third data, the rated load of the micro pipe jacking machine, the rated system pressure, the rated hydraulic pump power, the first proportional coefficient, the first integral coefficient and the first differential coefficient to calculate the second proportional coefficient, the second integral coefficient and the second differential coefficient; presetting the initial proportional coefficient, the initial integral coefficient and the initial differential coefficient, and combining the second proportional coefficient, the second integral coefficient and the second differential coefficient to calculate the fourth data.

[0014] The above scheme combines the predicted data obtained by the neural network model and the collected second data, and processes them through a fuzzy proportional-integral-differential controller to obtain a more effective fourth data, that is, the proportional, integral, and differential coefficients of the jacking speed error of the micro pipe jacking machine.

[0015] Preferably, controlling the jacking speed of the micro pipe jacking machine according to the fourth data includes: adjusting the frequency of a host inverter according to the fourth data to achieve control of the jacking speed of the micro pipe jacking machine.

[0016] The above scheme can adjust the frequency of the host inverter through the fourth data to respond quickly and accurately, and control the jacking speed more timely.

[0017] Preferably, the host frequency converter frequency is adjusted according to the fourth data to achieve control of the jacking speed of the micro pipe jacking machine, including: the host frequency converter adjusts the hydraulic system of the micro pipe jacking machine to achieve control of the jacking speed of the pipe jacking machine.

[0018] In a second aspect, the present invention further provides a jacking speed control system for a micro pipe jacking machine, comprising: a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the above-mentioned jacking speed control method for a micro pipe jacking machine.

[0019] The beneficial effect of the present invention is that: by combining the neural network with the fuzzy controller, the neural network can timely predict the third data of the micro pipe jacking machine, and then combine the predicted third data with the collected second data and input them into the proportional-integral-differential controller, so as to timely control the micro pipe jacking machine to adjust the jacking speed at the next moment, and no longer rely on manual or simple controllers. The neural network can realize intelligent regulation of the jacking speed, thereby solving the problem of failure caused by the unintelligent adjustment of the jacking speed of the micro pipe jacking machine in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0021] Figure 1 It is a flow chart of a method for controlling the jacking speed of a micro pipe jacking machine provided by an embodiment of the present invention;

[0022] Figure 2 This is a flow chart of another method for controlling the jacking speed of a micro pipe jacking machine provided by an embodiment of the present invention.

[0023] Figure 3The present invention provides a block diagram of a jacking speed control system for a micro pipe jacking machine. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical invention in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0025] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0026] Figure 1 is a flow chart of a method for controlling the jacking speed of a micro pipe jacking machine according to an embodiment of the present invention, comprising the following steps:

[0027] S101, collecting first data and second data, wherein the first data is the load, system pressure, and hydraulic pump power of the micro pipe jacking machine at the current moment, and the second data is the jacking speed error and speed error change rate of the micro pipe jacking machine at the current moment;

[0028] In the first data, the load, system pressure and hydraulic pump power of the micro pipe jacking machine are important parameters that reflect the operating status of the equipment and are closely related to the construction environment and formation conditions. The more difficult the formation is to penetrate, the higher these indicators will usually be.

[0029] In the second data, the micro-pipe jacking machine's jacking speed error and speed error change rate are time-varying variables, which are important indicators for evaluating the operating accuracy and stability of the pipe jacking machine. The jacking speed error refers to the difference between the actual jacking speed and the preset or expected jacking speed. Ideally, the pipe jacking machine should advance at a constant speed, but in actual operation, the speed of the equipment may fluctuate due to factors such as load changes, geological conditions, and hydraulic system response. The smaller the jacking speed error, the more precise the control of the equipment and the more the preset speed matches the geological conditions. For example, in an underground pipeline construction, the preset jacking speed is 10 mm / min, and the pipe jacking machine works in soft soil. The actual jacking speed is 9.8 mm / min, and the speed error is 0.2 mm / min, which is a small error. When encountering harder soil, the actual jacking speed drops to 9 mm / min, and the speed error increases to 1 mm / min. At this time, the error is large, and the pipe jacking machine needs to adjust the jacking speed to adapt to the new geological conditions. The speed error change rate refers to the rate of change of the jacking speed error over time. It reflects how the speed error of the pipe jacking machine gradually increases, decreases, or remains unchanged over time. The speed error change rate can help determine the stability of speed control: if the change rate is large, it means that the speed error is fluctuating rapidly and the geological conditions that may be encountered are more complex; if the change rate is small, it means that the speed control is relatively stable. For example, in the operation of a micro pipe jacking machine, the preset jacking speed is 10 mm / min. The actual speed measured at the first moment is 9.8 mm / min, and the speed error is 0.2 mm / min. The actual speed measured at the second moment is 9.5 mm / min, and the speed error is 0.5 mm / min. The time difference between the first moment and the second moment is one minute. The speed error change rate is the ratio of the speed error change to time, that is, mm / min 2 .

[0030] S102, predicting third data of the micro pipe jacking machine according to the first data and a pre-trained neural network model;

[0031] S103, combining the second data and the third data, using a fuzzy proportional-integral-differential controller to obtain fourth data, and controlling the jacking speed of the micro pipe jacking machine according to the fourth data.

[0032] In some embodiments, the third data is the load, system pressure and hydraulic pump power of the micro pipe jacking machine at the next moment; the fourth data is the proportion, integral and differential coefficient of the jacking speed error of the micro pipe jacking machine.

[0033] Training the neural network generally includes: collecting fifth data, the fifth data being the load, system pressure, hydraulic pump power of the micro-pipe jacking machine at multiple previous moments and the corresponding load, system pressure, hydraulic pump power of the micro-pipe jacking machine at the next moment; preprocessing the fifth data to obtain sixth data; and using the sixth data to train the convolutional neural network to obtain a neural network model. Generally, a convolutional neural network model can be used to train it to predict the load, system pressure, and hydraulic pump power of the micro-pipe jacking machine at the next moment.

[0034] In some embodiments, in order to improve the accuracy of the above neural network model and reduce the impact of abnormal data or noise data on the entire neural network model, it is also necessary to pre-process the training data, that is, the fifth data, including: correcting the abnormal data in the fifth data; using wavelet transform to denoise the fifth data. Generally speaking, the abnormal data can be corrected by deleting abnormal values, filling abnormal values ​​(such as mean filling, median filling, interpolation method and model prediction method) and sliding average method.

[0035] In some embodiments, the second data and the third data are combined, and a fuzzy proportional-integral-differential controller is used to obtain fourth data, and the jacking speed of the micro pipe jacking machine is controlled according to the fourth data, specifically including: fuzzifying, fuzzy reasoning and defuzzifying the second data to obtain a first proportional coefficient, a first integral coefficient and a first differential coefficient; combining the third data, the rated load of the micro pipe jacking machine, the rated system pressure, the rated hydraulic pump power, the first proportional coefficient, the first integral coefficient and the first differential coefficient to calculate the second proportional coefficient, the second integral coefficient and the second differential coefficient; presetting the initial proportional coefficient, the initial integral coefficient and the initial differential coefficient, and combining the second proportional coefficient, the second integral coefficient and the second differential coefficient to calculate the fourth data.

[0036] In some embodiments, controlling the jacking speed of the micro pipe jacking machine according to the fourth data includes: adjusting the frequency of the host frequency converter according to the fourth data to achieve control of the jacking speed of the micro pipe jacking machine, the frequency converter usually controls the motor that drives the hydraulic pump or directly drives the jacking system, thereby controlling the jacking speed of the micro pipe jacking machine.

[0037] like Figure 2 The figure shows another method for controlling the jacking speed of a micro pipe jacking machine provided by an embodiment of the present invention. Where e(t) and Δe are input variables that change with time, e(t) is the jacking speed error, Δe is the rate of change of the jacking speed error, and ΔK p is the adaptive proportional coefficient, ΔK i is the adaptive integral coefficient, ΔK d is the adaptive differential coefficient, K p ' is the initial proportional coefficient, K i' is the initial integration coefficient, K d ' is the initial differential coefficient, K p is the proportionality coefficient, K i is the integration coefficient, K d is the differential coefficient, and u(t) is the controller output.

[0038] Generally speaking, the process has the following steps:

[0039] Step 1: Install multiple sensors on the micro pipe jacking machine to collect the current load, system pressure, and hydraulic pump power, and use the CNN convolutional neural network model to predict the load, system pressure, and hydraulic pump power at the next moment;

[0040] Step 2: Input the speed error e(t) and the speed error change rate Δe, convert them into a fuzzy set through fuzzification, perform fuzzy reasoning on the fuzzy set according to fuzzy rules, generate fuzzy output, and then convert the fuzzy output into a specific adaptive coefficient ΔK through defuzzification. p , ΔK i and ΔK d ;

[0041] For example, the fuzzy processing of the speed error e can be set to five fuzzy sets of "negative large (NB)", "negative small (NS)", "zero (ZE)", "positive small (PS)", and "positive large (PB)", and the fuzzy set to which it belongs is determined according to the size of the speed error e. Similarly, the fuzzy processing of the speed error change rate Δe can be set to five fuzzy sets of "negative large (NB)", "negative small (NS)", "zero (ZE)", "positive small (PS)", and "positive large (PB)", and the fuzzy set to which it belongs is determined according to the size of the speed error change rate Δe. According to the preset fuzzy rules, the fuzzy set of the speed error e(t), the fuzzy set of the speed error change rate Δe and the adaptive coefficient ΔK are combined. p , ΔK i , ΔK d For example, the fuzzy rule is that if the speed error e(t) is "positive and large" and the speed error change rate Δe is "negative and small", then the adaptive proportional coefficient ΔK p The fuzzy set it belongs to is "medium", the speed error e(t) is "zero" and the speed error change rate Δe is "zero", then the adaptive integral coefficient ΔK i The fuzzy set it belongs to is "low", the speed error e(t) is "negative small" and the speed error change rate Δe is "positive large", then the adaptive differential coefficient ΔK d The fuzzy set it belongs to is the "high" rule. Get the adaptive coefficient ΔK p , ΔK i , ΔK dAfter the fuzzy set to which it belongs, and then through defuzzification, the specific ΔK can be obtained p , ΔK i , ΔK d It should be noted that the specific fuzzification, fuzzy reasoning and defuzzification methods are well-known technologies and there are more than one, which will not be described in detail here.

[0042] Step 3: Combine the adaptive coefficient ΔK p , ΔK i , ΔK d , initial coefficient K p ', K i ', K d 'And the predicted load L, system pressure F, hydraulic pump power Q and rated load L at the next moment 额定 , Rated system pressure F 额定 , Rated hydraulic pump power Q 额定 , the final proportional coefficient K is obtained through the first operation, the second operation and the third operation respectively p , integral coefficient K i and the differential coefficient K d , the final output u(t) is obtained through a proportional-integral-derivative controller (PID controller). The micro pipe jacking machine can generally adjust the frequency of the host inverter according to the output u(t). By adjusting the output frequency of the inverter, the speed of the motor can be controlled. The motor controlled by the inverter is usually the motor that drives the hydraulic pump or directly drives the jacking system, thereby controlling the jacking speed of the micro pipe jacking machine.

[0043] For example, the first operation can be The second operation can be K i =ΔK i ×(|L 预测 -L 额定 |×Δt)×

[0044] (|F 预测 -F 额定 |×Δt)×(|Q 预测 -Q 额定 |×Δt)+K i ′, the third operation can be Where Δt is the time difference between the current moment and the next moment, and the final output is

[0045] The present invention combines a neural network with a fuzzy controller. The neural network can timely predict the third data of the micro pipe jacking machine, and then combine the predicted third data with the collected second data and input them into the proportional-integral-differential controller, so as to timely control the micro pipe jacking machine to adjust the jacking speed at the next moment, and no longer rely on manual or simple controllers. The neural network can realize intelligent regulation of the jacking speed, thereby solving the problem of failure caused by the unintelligent adjustment of the jacking speed of the micro pipe jacking machine in the prior art.

[0046] The present invention also provides a jacking speed control system for a micro pipe jacking machine. Figure 3 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for controlling the jacking speed of a micro pipe jacking machine described in the present invention is implemented.

[0047] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0048] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of or accessible to or connectable to a workshop device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0049] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0050] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternative inventions to the embodiments of the present invention described herein may be employed.

Claims

1. A method for controlling the jacking speed of a micro pipe jacking machine, characterized in that: include: Collecting first data and second data, wherein the first data is the load, system pressure, and hydraulic pump power of the micro pipe jacking machine at the current moment, and the second data is the jacking speed error and speed error change rate of the micro pipe jacking machine at the current moment; Predicting third data of the micro pipe jacking machine according to the first data and the pre-trained neural network model; the third data is the load, system pressure and hydraulic pump power of the micro pipe jacking machine at the next moment; Combining the second data and the third data, a fuzzy proportional-integral-differential controller is used to obtain fourth data, and the jacking speed of the micro pipe jacking machine is controlled according to the fourth data, wherein the fourth data is the proportional, integral, and differential coefficients of the jacking speed error of the micro pipe jacking machine; Combined with the adaptive coefficients ∆Kp, ∆Ki, ∆Kd, the initial coefficients Kp', Ki', Kd' and the predicted load L at the next moment, the system pressure F, the hydraulic pump power Q and the rated load L 额定 , Rated system pressure F 额定 , Rated hydraulic pump power Q 额定 , the final proportional coefficient Kp, integral coefficient Ki and differential coefficient Kd are obtained through the first operation, the second operation and the third operation respectively, and the final output u(t) is obtained through the proportional-integral-differential controller; the frequency of the host inverter is adjusted according to the output u(t), and the speed of the motor is controlled by adjusting the output frequency of the inverter; wherein, The first operation is: ； The second operation is: K i =ΔK i ×(|L 预测 -L 额定 |×Δt)×(|F 预测 -F 额定 |×Δt)×(|Q 预测 -Q 额定 |×Δt)+K i ′; The third operation is: ； In the formula, is the time difference between the current moment and the next moment; Final Output .

2. The method for controlling the jacking speed of a micro pipe jacking machine according to claim 1, characterized in that: The pre-trained neural network model comprises: Collecting fifth data, wherein the fifth data is the load, system pressure, and hydraulic pump power of the micro pipe jacking machine at multiple previous moments and the corresponding load, system pressure, and hydraulic pump power of the micro pipe jacking machine at the next moment; preprocessing the fifth data to obtain sixth data; The sixth data is used to train a convolutional neural network to obtain a neural network model.

3. The method for controlling the jacking speed of a micro pipe jacking machine according to claim 2, characterized in that: Preprocessing the fifth data includes: Correcting abnormal data in the fifth data; The fifth data is denoised using wavelet transform.

4. The method for controlling the jacking speed of a micro pipe jacking machine according to claim 1, characterized in that: The method combines the second data and the third data, obtains fourth data by using a fuzzy proportional-integral-differential controller, and controls the jacking speed of the micro pipe jacking machine according to the fourth data, including: Fuzzifying, fuzzy reasoning and defuzzifying the second data to obtain a first proportional coefficient, a first integral coefficient and a first differential coefficient; The second proportional coefficient, the second integral coefficient and the second differential coefficient are calculated by combining the third data, the rated load of the micro pipe jacking machine, the rated system pressure, the rated hydraulic pump power, the first proportional coefficient, the first integral coefficient and the first differential coefficient; An initial proportional coefficient, an initial integral coefficient and an initial differential coefficient are preset, and the fourth data is calculated by combining the second proportional coefficient, the second integral coefficient and the second differential coefficient.

5. The method for controlling the jacking speed of a micro pipe jacking machine according to claim 4, characterized in that: The controlling the jacking speed of the micro pipe jacking machine according to the fourth data comprises: The frequency of the host inverter is adjusted according to the fourth data to control the jacking speed of the micro pipe jacking machine.

6. The method for controlling the jacking speed of a micro pipe jacking machine according to claim 5, characterized in that: The host frequency converter frequency is adjusted according to the fourth data to achieve control of the micro pipe jacking machine's jacking speed, including: the host frequency converter adjusts the micro pipe jacking machine's hydraulic system to achieve control of the micro pipe jacking machine's jacking speed.

7. A jacking speed control system for a micro pipe jacking machine, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method for controlling the jacking speed of the micro pipe jacking machine as described in any one of claims 1 to 6.

Images