Hydraulic energy-saving control system and method for movable arm of engineering machinery

Abstract

The invention relates to the technical field of energy-saving control, and discloses an engineering machinery movable arm hydraulic energy-saving control system and method.The engineering machinery movable arm hydraulic energy-saving control system comprises a data acquisition module used for acquiring PID parameters, input signals, output signals, output power and state variables of a movable arm hydraulic system, and outputting the PID parameters, the input signals, the output signals, the output power and the state variables; representing through a first feature sequence; the data preprocessing module is used for preprocessing the first feature sequence to obtain a second feature sequence; the response time prediction module is used for constructing a response time prediction model according to the second feature sequence and outputting the response time of the system under the current PID parameter combination; and the parameter combination generation module is used for generating a PID parameter combination according to the response time of the system under the current PID parameter combination in combination with a particle swarm algorithm introduced with a t distribution disturbance variation strategy. The energy-saving effect of the movable arm hydraulic control system is maximized.

Description

Technical Field

[0001] The invention belongs to the technical field of energy saving, and in particular relates to a hydraulic energy saving control system and method for a movable arm of an engineering machinery. Background Art

[0002] In the traditional hydraulic control system of engineering machinery boom, hydraulic drive is widely used to provide stable and powerful execution force to meet the needs of boom operation. However, the traditional hydraulic control system has great shortcomings in energy efficiency and energy saving.

[0003] Therefore, there is an urgent need for a boom hydraulic energy-saving control system to solve the above problems. Summary of the invention

[0004] The present invention provides a hydraulic energy-saving control system and method for a movable arm of an engineering machinery, which solves the technical problems of low energy consumption efficiency and no energy saving in related technologies.

[0005] The present invention provides a hydraulic energy-saving control system and method for a boom of an engineering machinery, comprising:

[0006] A data acquisition module, which is used to collect PID parameters, input signals, output signals, output power and state variables of the boom hydraulic system within a preset time period T according to a preset time interval t, and represent them through a first characteristic sequence, where T and t are custom parameters;

[0007] The first characteristic sequence includes N sequence units, and the nth sequence unit of the first characteristic sequence represents the PID parameters, input signals, output signals, output power and state variables of the nth time period, wherein N=T / t, 1≤n≤N;

[0008] The PID parameters include: proportional gain, integral gain and differential gain; the input signals include: boom position, boom speed and pressure; the output signals include: boom position, boom speed and pressure; the state variables include: oil temperature, boom load and ambient temperature;

[0009] A data preprocessing module, which is used to preprocess the first feature sequence to obtain a second feature sequence;

[0010] A response time prediction module, which is used to construct a response time prediction model according to the second feature sequence, the input of the response time prediction model is the second feature sequence, and the output is the response time of the system under the current PID parameter combination;

[0011] The parameter combination generation module is used to generate a PID parameter combination according to the response time of the system under the current PID parameter combination and the particle swarm algorithm introduced with the t-distribution disturbance mutation strategy.

[0012] Furthermore, the boom position and boom speed are encoded using real numbers, wherein the boom position at time t represents the distance of the boom relative to the initial position at time t.

[0013] Furthermore, the step of preprocessing the first feature sequence includes:

[0014] Step S201, using the 3σ criterion to detect outliers in the first feature sequence, and replacing the outliers with the median;

[0015] Step S202, using mean filling processing for missing values ​​in the first feature sequence;

[0016] Step S203: preprocess the first feature sequence using the maximum-minimum normalization method to obtain a second feature sequence.

[0017] Furthermore, the response time prediction model includes: a hidden layer, an extraction layer and a classifier;

[0018] The hidden layer includes N first units, the nth first unit inputs the nth sequence unit of the second feature sequence, and outputs the first feature vector;

[0019] The extraction layer is used to extract the Nth first eigenvector output by the Nth first unit and represent it by the second eigenvector;

[0020] The second feature vector is input into the classifier, and the classification space of the classifier represents the response time of the system under the current PID parameters.

[0021] Furthermore, the hidden layer is constructed based on an improved gated recurrent unit, and the improvements include: introducing an adjustment coefficient in an update gate, introducing a scaling factor in a reset gate, introducing a residual connection, and adding a trend gate.

[0022] Furthermore, manual annotation is used as sample labels for training the response time prediction model.

[0023] Furthermore, the steps of generating a PID parameter combination according to the response time prediction model combined with a particle swarm algorithm that introduces a t-distribution perturbation mutation strategy include:

[0024] Step S301, randomly generating an initial particle swarm with a size of U that satisfies specific constraints;

[0025] Step S302, constructing an objective function in combination with a response time prediction model;

[0026] Step S303, calculating the fitness values ​​of all particles in the particle swarm according to the objective function;

[0027] Step S304, updating the particle positions and velocities in the next generation particle swarm according to the particle swarm algorithm update strategy and the t-distribution perturbation mutation strategy;

[0028] Step S305, if it is determined that the fitness value of each particle in the initialization particle swarm with the current iteration number j is greater than the maximum fitness value of the particle in history, the maximum fitness value of the particle in history is replaced by the fitness value of the particle with the current iteration number j, and the maximum fitness value in the initialization particle swarm with the current iteration number j is taken as the global optimal solution;

[0029] Step S306, the current number of iterations is increased by 1, and if it is determined that the current number of iterations reaches the maximum number of iterations, the global optimal solution is output as the PID parameter combination, otherwise, the process returns to step S303, where the maximum number of iterations is a custom parameter.

[0030] Furthermore, the objective function of the particle swarm algorithm is:

[0031]

[0032] Among them, F represents the fitness value of the objective function, E represents the power under the current PID parameter combination, R represents the response time under the current PID parameter combination output according to the response time prediction model, and ω1 and ω2 represent the power weight coefficient and the time weight coefficient respectively.

[0033] The present invention provides a hydraulic energy-saving control method for an engineering machinery boom, comprising the following steps:

[0034] Step S401, collecting PID parameters, input signals, output signals, output power and state variables of the boom hydraulic system, and representing them through a first characteristic sequence;

[0035] Step S402, preprocessing the first feature sequence to obtain a second feature sequence;

[0036] Step S403, constructing a response time prediction model according to the second feature sequence, and outputting the response time of the system under the current PID parameter combination;

[0037] Step S404: Generate a PID parameter combination according to the response time of the system under the current PID parameter combination and a particle swarm algorithm with a t-distribution disturbance mutation strategy.

[0038] The beneficial effects of the present invention are as follows: the present invention can dynamically optimize the PID parameter combination by constructing a response time prediction model and combining the particle swarm algorithm with the introduction of the t-distribution perturbation mutation strategy, so as to minimize the energy consumption of the hydraulic system under various working conditions and maximize the energy saving effect;

[0039] The particle swarm algorithm in the present invention introduces a t-distribution perturbation strategy, so that the algorithm enhances the ability to jump out of the local optimum, thereby ensuring that the system can maintain good control performance and rapid response under various working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a module schematic diagram of a hydraulic energy-saving control system for an engineering machinery boom of the present invention;

[0041] Figure 2 is a flow chart of preprocessing the first feature sequence of the present invention;

[0042] Figure 3 It is a flow chart of the particle swarm algorithm of the present invention that introduces the t-distribution perturbation mutation strategy.

[0043] In the figure: a data acquisition module 101, a data preprocessing module 102, a response time prediction module 103 and a parameter combination generation module 104. DETAILED DESCRIPTION

[0044] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the present specification. Various examples may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0045] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in one or more embodiments of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0046] like Figure 1-Figure 3 As shown, a hydraulic energy-saving control system and method for an engineering machinery boom includes:

[0047] The data acquisition module 101 is used to collect PID parameters, input signals, output signals, output power and state variables of the boom hydraulic system within a preset time period T according to a preset time interval t, and represent them through a first characteristic sequence, where T and t are custom parameters;

[0048] The first characteristic sequence includes N sequence units, and the nth sequence unit of the first characteristic sequence represents the PID parameters, input signals, output signals, output power and state variables of the nth time period, wherein N=T / t, 1≤n≤N;

[0049] The PID parameters include: proportional gain, integral gain and differential gain, the input signals include: boom position, boom speed and pressure, the output signals include: boom position, boom speed and pressure, and the state variables include: oil temperature, boom load and ambient temperature;

[0050] A data preprocessing module 102, which is used to preprocess the first feature sequence to obtain a second feature sequence;

[0051] A response time prediction module 103, which is used to construct a response time prediction model according to the second feature sequence, the input of the response time prediction model is the second feature sequence, and the output is the response time of the system under the current PID parameter combination;

[0052] The parameter combination generating module 104 is used to generate a PID parameter combination according to the response time of the system under the current PID parameter combination and the particle swarm algorithm introduced with the t-distribution disturbance mutation strategy.

[0053] In one embodiment of the present invention, the boom position and boom speed are encoded using real numbers, wherein the boom position at time t represents the distance of the boom relative to the initial position at time t.

[0054] In one embodiment of the present invention, the step of preprocessing the first feature sequence includes:

[0055] Step S201, using the 3σ criterion to detect outliers in the first feature sequence, and replacing the outliers with the median;

[0056] Step S202, using mean filling processing for missing values ​​in the first feature sequence;

[0057] Step S203: preprocess the first feature sequence using the maximum-minimum normalization method to obtain a second feature sequence.

[0058] In one embodiment of the present invention, the response time prediction model includes: a hidden layer, an extraction layer and a classifier;

[0059] The hidden layer includes N first units, the nth first unit inputs the nth sequence unit of the second feature sequence, and outputs the first feature vector;

[0060] The extraction layer is used to extract the Nth first eigenvector output by the Nth first unit and represent it by the second eigenvector;

[0061] The second feature vector is input into the classifier, and the classification space of the classifier represents the response time of the system under the current PID parameters.

[0062] In one embodiment of the present invention, the hidden layer is constructed based on the improved gated recurrent unit, and the specific improvements include: adding an adjustment coefficient in the update gate, adding a scaling factor in the reset gate, embedding a residual connection, and introducing a trend gate. In these improvements, the adjustment coefficient is used to flexibly adjust the influence of the hidden state at the previous moment, so that the model can more easily balance the proportion of historical information and current input, thereby improving the accuracy and adaptability of the prediction; adding a scaling factor in the reset gate to reduce the interference of short-term fluctuations on the model, helping the model to more accurately retain key long-term trend information, avoiding overreaction caused by short-term noise, and making the model more stable in dynamic changes; through residual connections, the original input information can be directly transmitted to subsequent levels to prevent the loss of key information when processing short-term fluctuations, and improve the model's expressiveness and anti-interference ability in complex time series; the trend gate specifically captures and retains the long-term trend information of the input data, so that the model has the ability to learn the data change pattern over a long period of time. Through this gated design, the model can effectively focus on long-term trends while processing short-term fluctuations, significantly improving the overall prediction effect.

[0063] Specifically, the calculation formula of the nth first unit of the hidden layer includes:

[0064] The calculation formula of the update gate of the first unit of the hidden layer n is:

[0065]

[0066] Among them, z n represents the update gate of the first unit of the hidden layer n, x n represents the nth sequence unit of the second feature sequence currently input, h n-1 represents the feature vector output by the first unit of the n-1th order, and They represent the first weight parameter, the second weight parameter and the bias parameter corresponding to the update gate of the nth sequence unit of the second feature sequence respectively, and α represents the adjustment coefficient, which is used to adjust the hidden state h at the previous moment. n-1 The weight in the update gate increases the sensitivity of the update gate to short-term changes;

[0067] The calculation formula of the reset gate of the first unit of the hidden layer n is:

[0068]

[0069] Among them, r n represents the reset gate of the first unit of the nth hidden layer, and denote the first weight parameter, the second weight parameter and the bias parameter corresponding to the reset gate of the nth sequence unit of the second feature sequence respectively, and β denotes a scaling factor, which is used to adjust the response speed of the reset gate to the current input and hidden state, prevent overreaction to short-term noise, and retain long-term information;

[0070] The calculation formula of the trend gate of the first unit of the nth hidden layer is:

[0071]

[0072] Among them, τ n represents the trend gate of the first unit of the nth hidden layer, and Respectively represent the first weight parameter, the second weight parameter and the bias parameter corresponding to the trend gate of the nth sequence unit of the second feature sequence;

[0073] The calculation formula for the candidate hidden state of the nth first unit in the hidden layer is:

[0074]

[0075] in, represents the candidate hidden state of the first unit of the hidden layer n, r n and Respectively represent a first weight parameter, a second weight parameter and a bias parameter corresponding to the candidate hidden state of the nth sequence unit of the second feature sequence;

[0076] The calculation formula for updating the hidden state of the first unit of the hidden layer is:

[0077]

[0078] Among them, h n represents the characteristic vector output by the first unit of the nth hidden layer, ⊙ represents point-by-point multiplication, and γ represents the weight coefficient of the residual connection, which controls the direct impact of the current input on the hidden state and prevents excessive smoothing of information.

[0079] In one embodiment of the present invention, manual annotation is used as sample labels for training the response time prediction model.

[0080] In one embodiment of the present invention, Figure 3 As shown, the steps of generating PID parameter combinations based on the response time prediction model combined with the particle swarm algorithm that introduces the t-distribution disturbance mutation strategy include:

[0081] Step S301, randomly generating an initial particle swarm with a size of U that satisfies specific constraints;

[0082] The constraints include: the pressure of the hydraulic system is within the preset pressure threshold range; the oil temperature of the hydraulic system is within the preset oil temperature threshold range; the boom speed is within the preset speed threshold range;

[0083] Each particle includes a position code and a velocity code;

[0084] The position encoding is represented by a vector X={kp, ki, kd}, where kp, ki and kd represent proportional gain, integral gain and differential gain respectively;

[0085] The velocity encoding is done by vector V =}kp v ,ki v , kd v { indicates that the value of each dimension of the velocity vector is Z% of the value of each dimension of the position vector, where Z is a custom parameter. Preferably, the value range of Z is 10 to 20;

[0086] Step S302, constructing an objective function in combination with a response time prediction model;

[0087] Step S303, calculating the fitness values ​​of all particles in the particle swarm according to the objective function;

[0088] Step S304, updating the particle positions and velocities in the next generation particle swarm according to the particle swarm algorithm update strategy and the t-distribution perturbation mutation strategy;

[0089] The particle velocity update formula is: j+1 =ωv j +c1r1(p j -x j )+c2r2(g j -x j )+τ*t γ (0, θ), where v j+1 represents the particle velocity at iteration number j+1, v j represents the particle velocity with iteration number j, ω represents the inertia weight, c1 and c2 represent learning factors, r1 and r2 represent random numbers ranging from 0 to 1, and p j represents the optimal position of the particle in history when the number of iterations is j, g j represents the global optimal position of the entire particle swarm, τ represents the disturbance intensity control parameter, and t γ(0, θ) represents a t-distributed random variable with mean 0 and scale θ, and γ represents the degrees of freedom of the t-distribution;

[0090] Step S305, if the fitness value of each particle in the initialized particle swarm with the current iteration number j is determined to be greater than the maximum fitness value of the particle in history, the maximum fitness value of the particle in history is replaced by the fitness value of the particle with the current iteration number j;

[0091] The maximum fitness value in the initialized particle swarm with the current iteration number j is taken as the global optimal solution;

[0092] Step S306, the current number of iterations is increased by 1, and if it is determined that the current number of iterations reaches the maximum number of iterations, the global optimal solution is output as the PID parameter combination, otherwise, the process returns to step S303, where the maximum number of iterations is a custom parameter, and preferably, the maximum number of iterations is set to 200.

[0093] In one embodiment of the present invention, the particle swarm algorithm introduces t-distribution perturbation, adding a random perturbation based on t-distribution to the velocity or position of the particle in each iteration. This perturbation has a thicker tail characteristic, can produce larger random jumps, help particles jump out of the local optimal area, and enhance the global search capability of the algorithm.

[0094] In one embodiment of the present invention, the objective function of the particle swarm algorithm is:

[0095]

[0096] Among them, F represents the fitness value of the objective function, E represents the power under the current PID parameter combination, R represents the response time under the current PID parameter combination output according to the response time prediction model, and ω1 and ω2 represent the power weight coefficient and the time weight coefficient respectively.

[0097] In one embodiment of the present invention, a hydraulic energy-saving control method for a boom of an engineering machinery is also provided, comprising the following steps:

[0098] Step S401, collecting PID parameters, input signals, output signals, output power and state variables of the boom hydraulic system, and representing them through a first characteristic sequence;

[0099] Step S402, preprocessing the first feature sequence to obtain a second feature sequence;

[0100] Step S403, constructing a response time prediction model according to the second feature sequence, and outputting the response time of the system under the current PID parameter combination;

[0101] Step S404: Generate a PID parameter combination according to the response time of the system under the current PID parameter combination and a particle swarm algorithm with a t-distribution disturbance mutation strategy.

[0102] The above describes an embodiment of the present embodiment, but the present embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present embodiment, ordinary technicians in this field can also make many forms, all of which are within the protection of the present embodiment.

Claims

1. A hydraulic energy-saving control system for an engineering machinery boom, characterized in that: include: A data acquisition module, which is used to collect PID parameters, input signals, output signals, output power and state variables of the boom hydraulic system within a preset time period T according to a preset time interval t, and represent them through a first characteristic sequence, where T and t are custom parameters; The first characteristic sequence includes N sequence units, and the nth sequence unit of the first characteristic sequence represents the PID parameters, input signals, output signals, output power and state variables of the nth time period, wherein N=T / t, 1≤n≤N; The PID parameters include: proportional gain, integral gain and differential gain; the input signals include: boom position, boom speed and pressure; the output signals include: boom position, boom speed and pressure; the state variables include: oil temperature, boom load and ambient temperature; A data preprocessing module, which is used to preprocess the first feature sequence to obtain a second feature sequence; A response time prediction module is used to construct a response time prediction model according to the second feature sequence, wherein the input of the response time prediction model is the second feature sequence, and the output is the response time of the system under the current PID parameter combination; The parameter combination generation module is used to generate a PID parameter combination according to the response time of the system under the current PID parameter combination and the particle swarm algorithm introduced with the t-distribution disturbance mutation strategy.

2. The hydraulic energy-saving control system for an engineering machinery boom according to claim 1 is characterized in that: The boom position and boom speed are encoded using real numbers, where the boom position at time t represents the distance of the boom relative to the initial position at time t.

3. The hydraulic energy-saving control system for an engineering machinery boom according to claim 1 is characterized in that: The step of preprocessing the first feature sequence includes: Step S201, using the 3σ criterion to detect outliers in the first feature sequence, and replacing the outliers with the median; Step S202, using mean filling processing for missing values ​​in the first feature sequence; Step S203: preprocess the first feature sequence using the maximum-minimum normalization method to obtain a second feature sequence.

4. The hydraulic energy-saving control system for an engineering machinery boom according to claim 1, characterized in that: The response time prediction model includes: a hidden layer, an extraction layer and a classifier; The hidden layer includes N first units, the nth first unit inputs the nth sequence unit of the second feature sequence, and outputs the first feature vector; The extraction layer is used to extract the Nth first eigenvector output by the Nth first unit and represent it by the second eigenvector; The second feature vector is input into the classifier, and the classification space of the classifier represents the response time of the system under the current PID parameters.

5. The hydraulic energy-saving control system for an engineering machinery boom according to claim 4, characterized in that: The hidden layer is constructed based on an improved gated recurrent unit, and the improvements include: introducing an adjustment coefficient in an update gate, introducing a scaling factor in a reset gate, introducing a residual connection, and adding a trend gate.

6. The hydraulic energy-saving control system for an engineering machinery boom according to claim 1, characterized in that: Manual annotation is used as sample labels for training the response time prediction model.

7. The hydraulic energy-saving control system for an engineering machinery boom according to claim 1, characterized in that: The steps of generating PID parameter combinations based on the response time prediction model combined with the particle swarm algorithm that introduces the t-distribution disturbance mutation strategy include: Step S301, randomly generating an initial particle swarm with a size of U that satisfies specific constraints; Step S302, constructing an objective function in combination with a response time prediction model; Step S303, calculating the fitness values ​​of all particles in the particle swarm according to the objective function; Step S304, updating the particle positions and velocities in the next generation particle swarm according to the particle swarm algorithm update strategy and the t-distribution perturbation mutation strategy; Step S305, if it is determined that the fitness value of each particle in the initialization particle swarm with the current iteration number j is greater than the maximum fitness value of the particle in history, the maximum fitness value of the particle in history is replaced by the fitness value of the particle with the current iteration number j, and the maximum fitness value in the initialization particle swarm with the current iteration number j is taken as the global optimal solution; Step S306, the current number of iterations is increased by 1, and if it is determined that the current number of iterations reaches the maximum number of iterations, the global optimal solution is output as the PID parameter combination, otherwise, the process returns to step S303, where the maximum number of iterations is a custom parameter.

8. The hydraulic energy-saving control system for an engineering machinery boom according to claim 7, characterized in that: The objective function of the particle swarm algorithm is: Among them, F represents the fitness value of the objective function, E represents the power under the current PID parameter combination, R represents the response time under the current PID parameter combination output according to the response time prediction model, and ω1 and ω2 represent the power weight coefficient and the time weight coefficient respectively.

9. A hydraulic energy-saving control method for a construction machinery boom, characterized in that: A hydraulic energy-saving control system for an engineering machinery boom as claimed in any one of claims 1 to 8 is adopted, comprising the following steps: Step S401, collecting PID parameters, input signals, output signals, output power and state variables of the boom hydraulic system, and representing them through a first characteristic sequence; Step S402, preprocessing the first feature sequence to obtain a second feature sequence; Step S403, constructing a response time prediction model according to the second feature sequence, and outputting the response time of the system under the current PID parameter combination; Step S404: Generate a PID parameter combination according to the response time of the system under the current PID parameter combination and a particle swarm algorithm with a t-distribution disturbance mutation strategy.

Images