Automatic adjusting method and system for workshop conveyor

Abstract

The invention provides an automatic adjusting method and system for a workshop conveyor, and relates to the technical field of workshop conveyors. The method comprises the following steps: collecting multi-dimensional data of a workshop conveyor in real time; performing feature extraction; the operation state of the workshop conveyor is evaluated in real time, and preliminary operation data adjustment is carried out; constructing an incidence relation network of the multi-dimensional data; establishing a multi-objective optimization model, and solving an optimal adjustment strategy; and converting the optimal adjustment strategy into a control instruction, and adjusting the operation data. Through intelligent data analysis and accurate parameter adjustment, the operation stability and the conveying efficiency are improved, energy consumption and equipment abrasion are reduced, high adaptability and flexibility are achieved, and remarkable economic benefits and social benefits are brought to modern industrial production.

Description

Technical Field

[0001] The present invention relates to the technical field of workshop conveyors, and particularly to an automatic adjustment method for a workshop conveyor and an automatic adjustment system for a workshop conveyor. Background Art

[0002] In the process of the intelligent transformation of modern manufacturing, as the core equipment for material transportation, the operating efficiency, energy consumption control, and equipment reliability of workshop conveyors directly affect the overall efficiency of the production line.

[0003] The invention patent with the publication number CN114634005A proposes a driving control method and system for a belt conveyor, which can automatically obtain the driving force required by the belt conveyor; obtain the power output state of the driving motor in each driving unit of the belt conveyor according to the required driving force, and adjust the driving ratio of each driving unit according to the power output state of each driving motor. The whole process is realized by automatic acquisition and control of information without manual participation. The characteristic of automation technology is that it can accurately record operation information. Therefore, when automatically adjusting the tension of the driving drum subsequently, the actual value of the driving ratio can be automatically known, and then the tension of the driving drum can be controlled according to the actual value of the driving ratio, and the whole process realizes unattended operation.

[0004] However, there are still many obvious defects in the existing workshop conveyor technology. Traditional monitoring methods are difficult to comprehensively and real-time capture the operating state of the conveyor. Subtle changes in motor current and abnormal fluctuations in component temperature are often not detected in time, resulting in some potential fault hazards that cannot be discovered and processed in time. Once these hazards develop into faults, it may cause equipment shutdown and production interruption, bringing serious economic losses to the enterprise. The operating parameters of the conveyor are often set fixedly and are difficult to be dynamically adjusted according to the actual situation. In the face of different working conditions, it is impossible to achieve precise adaptation, resulting in problems such as unreasonable speed and material accumulation during the conveying process, greatly reducing the conveying efficiency. Due to the inability to accurately adjust the operating parameters of the conveyor in real time, during the long-term operation of the equipment, each component bears uneven stress and friction, resulting in increased wear. Frequent equipment wear not only shortens the service life of the equipment, increases the equipment maintenance cost and replacement frequency, but also may affect the production progress due to equipment failures. Summary of the Invention

[0005] The present invention provides an automatic adjustment method and system for a workshop conveyor to solve the defects existing in the prior art.

[0006] On the one hand, the present invention provides an automatic adjustment method for a workshop conveyor, including: Collect multi-dimensional data of the workshop conveyor in real time. The multi-dimensional data includes operation data, environmental data, and material data.

[0007] Use the wavelet transform method to denoise the multi-dimensional data, and perform feature extraction using principal component analysis to obtain operation features, environmental features, and material features.

[0008] Construct an evaluation model based on support vector machines. According to the operation features, environmental features, and material features, evaluate the operation status of the workshop conveyor in real time, and adjust the initial operation data according to the operation status according to preset rules.

[0009] Adopt the Kalman filtering algorithm to fuse the multi-dimensional data, and use the long short-term memory network to construct the correlation relationship network of the multi-dimensional data.

[0010] Establish a multi-objective optimization model for comprehensive conveying efficiency, energy consumption, and equipment wear according to the correlation relationship network. Use the multi-objective evolutionary algorithm to solve the multi-objective optimization model to obtain a set of adjustment strategies, and select the optimal adjustment strategy for the current working condition through the fuzzy decision-making theory.

[0011] Utilize servo drive and variable frequency speed regulation technologies, convert the optimal adjustment strategy into control instructions through a programmable logic controller, and combine feedforward and feedback control to adjust the operation data.

[0012] According to an automatic adjustment method for a workshop conveyor provided by the present invention, the operation data includes operation speed, motor current, conveyor belt tension, and the rotation speed of the rotating parts of the conveyor. The environmental data includes the temperature of the conveyor components and the operation sound. The material data includes the weight, volume, shape, density, and distribution of the material.

[0013] According to an automatic adjustment method for a workshop conveyor provided by the present invention, the process of performing feature extraction using principal component analysis includes: Construct a multi-dimensional data matrix. For each feature in the multi-dimensional data matrix, calculate its mean and standard deviation to obtain the standardized data and the covariance matrix.

[0014] Perform eigenvalue decomposition on the covariance matrix. According to the magnitude of the eigenvalues, select the eigenvectors corresponding to the first k largest eigenvalues as the principal components to obtain the operation features, environmental features, and material features.

[0015] According to an automatic adjustment method for a workshop conveyor provided by the present invention, the process of constructing an evaluation model based on support vector machines includes: Collect historical working condition multi-dimensional data samples of the conveyor. Suppose there are s samples of the collected historical data, and each sample contains g features, which are represented as a feature matrix , where is the feature vector of the i-th sample, and the corresponding operating status label is .

[0016] Define the Gaussian kernel function, which is expressed by the formula:

[0017] In the formula, and represent the feature vectors of the i-th sample and the j-th sample, represents the square of the Euclidean distance between the i-th sample and the j-th sample, represents the bandwidth parameter of the Gaussian kernel.

[0018] Introduce slack variables to construct an optimization problem, which is expressed by the formula:

[0019]

[0020] In the formula, w represents the weight vector, b is the bias term, represents the vector after mapping to the high-dimensional space, C represents the penalty parameter, represents the i-th operating status label, represents the slack variable.

[0021] Convert the optimization problem into a dual problem, use the sequential minimal optimization algorithm to solve the dual problem, calculate the weight vector and the bias term, and obtain the evaluation model.

[0022] According to an automatic adjustment method for a workshop conveyor provided by the present invention, the process of constructing an association relationship network of multi-dimensional data by using a long short-term memory network includes: Use the multi-dimensional data after Kalman filter fusion as the input of the long short-term memory network to obtain an input sequence.

[0023] Set the structure of the long short-term memory network, including an input layer, a hidden layer, and an output layer. The input layer is used to receive the input sequence. The hidden layer contains multiple long short-term memory network units, which are used to capture the long-term dependence relationship in the input sequence. The output layer is used to output the hidden state of each multi-dimensional data in the input sequence.

[0024] Train the long short-term memory network to analyze the time series association relationship between each multi-dimensional data.

[0025] Use the hidden state as a node, and the connection weight between the nodes represents the association strength between the data, to obtain the association relationship network of multi-dimensional data.

[0026] An automatic adjustment method for a workshop conveyor according to the present invention. The process of establishing a multi-objective optimization model considering comprehensive conveying efficiency, energy consumption, and equipment wear based on the correlation relationship network includes: Define the conveying efficiency as the ratio of the weight of the conveyed material per unit time to the maximum conveying capacity, and calculate the conveying efficiency based on the weight of the conveyed material per unit time and the maximum conveying capacity of the conveyor.

[0027] Define the energy consumption as the power consumption of the motor, and calculate the energy consumption based on the motor power and the running time.

[0028] Establish a wear model based on the tension change of the conveyor belt and the motor load.

[0029] Establish a comprehensive objective function as the multi-objective optimization model based on the conveying efficiency, energy consumption, and equipment wear.

[0030] An automatic adjustment method for a workshop conveyor according to the present invention. The process of using a multi-objective evolutionary algorithm to solve the multi-objective optimization model and obtain the solution set of adjustment strategies includes: Randomly generate a certain number of individuals as the initial population, where an individual represents a running data vector.

[0031] For each individual, calculate its comprehensive objective function value.

[0032] Use the non-dominated sorting and crowding distance sorting methods to select excellent individuals to enter the next generation.

[0033] Perform crossover and mutation operations on the selected individuals to generate new individuals.

[0034] Merge the newly generated individuals with the original population, and perform non-dominated sorting and crowding distance sorting again to select a certain number of individuals to form the next generation population.

[0035] When the preset termination condition is met, use the individuals in the current population as the solution set of adjustment strategies.

[0036] An automatic adjustment method for a workshop conveyor according to the present invention. The process of selecting the optimal adjustment strategy for the current working condition through fuzzy decision theory includes: Determine the factor set and the evaluation set. The factors in the factor set respectively correspond to the conveying efficiency, energy consumption, and equipment wear; the evaluations in the evaluation set represent the quality levels of the adjustment strategies. For each factor, determine its membership function according to the performance of each strategy in the solution set of adjustment strategies under this factor, and obtain the fuzzy relation matrix. According to the requirements of the current working condition, determine the weight vector of each factor. Calculate the fuzzy comprehensive evaluation vector, and based on the values of the elements in the fuzzy comprehensive evaluation vector, select the adjustment strategy corresponding to the element with the largest membership degree as the optimal adjustment strategy for the current working condition.

[0037] According to an automatic adjustment method for a workshop conveyor provided by the present invention, the process of combining feedforward and feedback control to adjust operation data includes: Receive the optimal adjustment strategy through a programmable logic controller, and extract the key adjustment parameters in the optimal adjustment strategy.

[0038] Establish a feedforward control model based on the physical characteristics and historical operation data of the workshop conveyor.

[0039] Using the feedforward control model, calculate the corresponding feedforward control instructions according to the key adjustment parameters.

[0040] Send the feedforward control instructions to the servo drive and variable frequency speed regulation equipment to adjust the operation data of the conveyor.

[0041] On the other hand, the present invention also provides an automatic adjustment system for a workshop conveyor, including: A data acquisition module for collecting multi-dimensional data of the workshop conveyor in real time. The multi-dimensional data includes operation data, environmental data, and material data.

[0042] A feature extraction module for denoising the multi-dimensions using the wavelet transform method and performing feature extraction using principal component analysis to obtain operation features, environmental features, and material features.

[0043] A preliminary adjustment module for constructing an evaluation model based on a support vector machine, evaluating the operation state of the workshop conveyor in real time according to the operation features, environmental features, and material features, and performing preliminary adjustment of the operation data according to the operation state according to preset rules.

[0044] An association relationship construction module for fusing multi-dimensional data using the Kalman filter algorithm and constructing an association relationship network of multi-dimensional data using a long short-term memory network.

[0045] An adjustment strategy generation module for establishing a multi-objective optimization model of comprehensive conveying efficiency, energy consumption, and equipment wear based on the association relationship network, solving the multi-objective optimization model using a multi-objective evolutionary algorithm to obtain a solution set of adjustment strategies, and selecting the optimal adjustment strategy for the current working condition through fuzzy decision theory.

[0046] A control adjustment module for using servo drive and variable frequency speed regulation technologies to convert the optimal adjustment strategy into control instructions through a programmable logic controller and combining feedforward and feedback control to adjust operation data.

[0047] An automatic adjustment method and system for a workshop conveyor provided by the present invention can timely detect abnormal situations during the operation of the conveyor by collecting multi-dimensional data in real time and performing denoising, feature extraction, and status evaluation, and adjust the initial operation data according to preset rules to avoid further deterioration of faults, thereby ensuring the continuous and stable operation of the conveyor and reducing production interruptions caused by equipment failures.

[0048] The data correlation network constructed by the long short-term memory network can deeply explore the internal relationships between multi-dimensional data. Combining the multi-objective optimization model and the fuzzy decision-making theory, the operating parameters of the conveyor, such as the operating speed and the conveyor belt tension, can be dynamically adjusted according to factors such as the current material characteristics and environmental conditions, enabling the conveyor to operate in an optimal state, quickly and efficiently complete the material conveying task, and greatly improving the production efficiency.

[0049] Through the multi-objective optimization model that comprehensively considers the conveying efficiency, energy consumption, and equipment wear, the energy consumption of the conveyor can be reduced as much as possible on the premise of ensuring the conveying efficiency. By accurately adjusting the operating parameters, unnecessary energy waste is avoided, and the balance between energy conservation and high efficiency is achieved. At the same time, reasonable adjustment of the operating parameters can also reduce the wear of the equipment, extend the service life of the equipment, and reduce the maintenance cost and replacement frequency of the equipment. Brief Description of the Drawings

[0050] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0051] Figure 1 It is a schematic flowchart of an automatic adjustment method for a workshop conveyor provided by an embodiment of the present invention; Figure 2 It is a schematic structural diagram of an automatic adjustment system for a workshop conveyor provided by an embodiment of the present invention. Detailed Embodiments

[0052] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0053] The following will be combined with Figure 1 - Figure 2Describe an automatic adjustment method and system for a workshop conveyor of the present invention.

[0054] Figure 1 It is a schematic flowchart of an automatic adjustment method for a workshop conveyor provided by an embodiment of the present invention.

[0055] As Figure 1 shown, an automatic adjustment method and system for a workshop conveyor provided by an embodiment of the present invention, the execution subject can be an automatic adjustment method for a workshop conveyor, and the method includes: Collect multi-dimensional data of the workshop conveyor in real time, and the multi-dimensional data includes operation data, environmental data, and material data.

[0056] The operation data includes operation speed, motor current, conveyor belt tension, and the rotation speed of the rotating components of the conveyor. The environmental data includes the temperature of the conveyor components and the operation sound. The material data includes the weight, volume, shape, density, and distribution of the materials.

[0057] The operation speed is collected using a speed sensor. The speed sensor is installed at a specific position on the drive shaft of the conveyor or the conveyor belt, and its linear speed or angular speed is measured by sensing the rotation of the shaft or the movement of the conveyor belt.

[0058] The current of the motor is measured using a current transformer. The current transformer is installed on the power supply line of the motor, converts the large current into a small current signal in proportion, and then converts it into an electrical signal that can be collected through a signal processing circuit.

[0059] The conveyor belt tension is measured using a tension sensor. The tension sensor is installed on the support roller or tensioning device of the conveyor belt, and the tension of the conveyor belt is determined by detecting the force exerted on the sensor by the conveyor belt.

[0060] The rotation speed of the rotating components of the conveyor is measured using a rotation speed sensor, such as a magnetoelectric rotation speed sensor or an optoelectronic rotation speed sensor. These sensors are installed near the rotating components (such as drums, gears, etc.), and the rotation speed information is obtained by detecting the rotation frequency of the rotating components.

[0061] A temperature sensor is used, such as a thermocouple or a thermal resistor. These sensors can be installed on the surfaces of key components of the conveyor (such as motors, bearings, etc.) to monitor the temperature changes of the components in real time.

[0062] The operation sound is collected using a sound sensor. The sound sensor is installed at a suitable position around the conveyor, can capture the sound signal generated during the operation of the conveyor, and convert it into an electrical signal.

[0063] A weighing sensor is installed at the feeding port or a specific position of the conveyor. When the material passes through the weighing sensor, the sensor will measure the weight of the material.

[0064] Measure the volume of the material using a volume measurement device, such as a laser scanner or an ultrasonic sensor. These devices can be installed above the conveyor to calculate the volume of the material by scanning its contour.

[0065] Use an industrial camera to capture the shape of the material. Install the industrial camera above or on the side of the conveyor, take pictures of the material, and then analyze the captured images through image processing technology to identify the shape characteristics of the material.

[0066] Calculate the density of the material according to the collected material weight and volume data through the density calculation formula.

[0067] Combine the industrial camera and image processing technology, or use multiple sensor arrays to detect the distribution position and distribution density of the material on the conveyor belt, and collect data on the distribution of the material.

[0068] By collecting information such as the running speed, motor current, conveyor belt tension, and rotational speed of the rotating parts of the conveyor in the operating data, the operating condition of the conveyor can be understood in real time. For example, an abnormal change in the motor current may mean that the motor load is too large or there is a fault; the instability of the conveyor belt tension may cause problems such as conveyor belt slipping or deviation. Combining the component temperature and operating sound in the environmental data can further determine whether the conveyor is in a normal operating state. For example, too high a component temperature may indicate component wear or poor heat dissipation; abnormal operating sounds may imply mechanical faults in the conveyor. After extracting the features of these data and inputting them into the evaluation model, the operating state of the conveyor can be accurately evaluated, providing a basis for subsequent operating adjustments.

[0069] Information such as weight, volume, shape, density, and distribution of the material in the material data is crucial for optimizing the operation of the conveyor. Materials with different weights and volumes have different load requirements for the conveyor. According to these characteristics of the material, the running speed and motor power of the conveyor can be reasonably adjusted to improve the conveying efficiency and reduce energy consumption. The shape and distribution of the material will affect the force uniformity and running stability of the conveyor belt. By collecting these data, corresponding adjustment measures can be taken to reduce equipment wear and extend the service life of the equipment.

[0070] At the same time, continuously collecting multi-dimensional data can establish an operating history database of the conveyor. By analyzing and mining the historical data, the changing trends and patterns of the data can be discovered. When certain data shows abnormal fluctuations, potential equipment failures can be predicted in advance, and maintenance measures can be taken in a timely manner to avoid production interruptions and economic losses caused by equipment failures.

[0071] Use the wavelet transform method to denoise the multi-dimensional data, and adopt principal component analysis for feature extraction to obtain operating features, environmental features, and material features.

[0072] The process of denoising multi-dimensional data using the wavelet transform method includes: Store the multi-dimensional data collected in real time from the workshop conveyor in the form of a matrix or vector, with the data of each dimension as a column of the matrix or an element of the vector.

[0073] According to the characteristics of the multi-dimensional data and the denoising requirements, select a suitable wavelet basis function, such as Haar wavelet, Daubechies wavelet, etc.

[0074] Determine the number of layers of wavelet decomposition. The choice of the decomposition layer will affect the denoising effect and needs to be reasonably selected according to the characteristics of the data and the noise level.

[0075] Perform wavelet decomposition on the organized multi-dimensional data. The specific operation is to decompose the original data into wavelet coefficients of different scales and frequencies through wavelet transform. In each layer of decomposition, the data is divided into approximation coefficients (low-frequency part) and detail coefficients (high-frequency part). The approximation coefficients represent the main characteristics of the data, while the detail coefficients contain the noise and high-frequency information in the data. Through multiple decompositions, the approximation coefficients and detail coefficients at different scales can be obtained.

[0076] Compare the detail coefficients with the selected threshold and process the detail coefficients according to the comparison results. Generally, there are two processing methods: hard thresholding and soft thresholding. Hard thresholding is to set the detail coefficients with absolute values less than the threshold to zero, while the detail coefficients with absolute values greater than the threshold remain unchanged; soft thresholding is to set the detail coefficients with absolute values less than the threshold to zero, while the detail coefficients with absolute values greater than the threshold are subtracted by the threshold.

[0077] After threshold processing the detail coefficients, perform wavelet reconstruction on the processed detail coefficients and the unprocessed approximation coefficients. Through the inverse wavelet transform, the approximation coefficients and the processed detail coefficients at different scales are combined to obtain the denoised multi-dimensional data.

[0078] The process of feature extraction using principal component analysis includes: Construct a multi-dimensional data matrix, which is expressed by the formula:

[0079] where n represents the number of samples, m represents the number of features, represents the j-th eigenvalue of the i-th sample.

[0080] For each feature, calculate its mean and standard deviation to obtain the standardized data and covariance matrix, which is expressed by the formula:

[0081]

[0082]

[0083]

[0084]

[0085] In the formula, represents the mean of the j-th feature, represents the standard deviation of the j-th feature, represents the data after standardization of the j-th feature of the i-th sample, Z represents the data matrix after standardization, and S represents the covariance matrix.

[0086] Perform eigenvalue decomposition on the covariance matrix, and the formula is expressed as:

[0087] In the formula, P represents the orthogonal matrix composed of eigenvectors, represents the diagonal matrix composed of eigenvalues.

[0088] According to the magnitude of the eigenvalues, select the eigenvectors corresponding to the top k largest eigenvalues as the principal components, and calculate the principal component scores to obtain the operation characteristics, environmental characteristics, and material characteristics.

[0089] The formula for the principal component score matrix is expressed as:

[0090] In the formula, represents the m×k matrix composed of the top k eigenvectors, and the principal component scores are the operation characteristics, environmental characteristics, and material characteristics extracted.

[0091] Construct an evaluation model based on the support vector machine. According to the operation characteristics, environmental characteristics, and material characteristics, evaluate the operation status of the workshop conveyor in real time, and adjust the initial operation data according to the operation status according to the preset rules.

[0092] The process of constructing an evaluation model based on the support vector machine includes: Collect multi-dimensional data samples of the historical working conditions of the conveyor. Suppose there are s samples of the collected historical data, and each sample contains g features, which are expressed as the feature matrix , where is the feature vector of the i-th sample, and the corresponding operation status label is .

[0093] Define the Gaussian kernel function, and the formula is expressed as:

[0094] Wherein, and represent the feature vectors of the i-th sample and the j-th sample, represents the square of the Euclidean distance between the i-th sample and the j-th sample, represents the bandwidth parameter of the Gaussian kernel.

[0095] By introducing slack variables, an optimization problem is constructed, and the formula is expressed as:

[0096]

[0097] Wherein, w represents the weight vector, b is the bias term, represents the vector after mapping to a high-dimensional space, C represents the penalty parameter, represents the label of the i-th operating state, represents the slack variable.

[0098] The optimization problem is transformed into a dual problem, and the formula is expressed as:

[0099]

[0100] Wherein, represents the Lagrange multiplier vector.

[0101] The sequential minimal optimization algorithm is used to solve the dual problem, and the values of and are continuously updated until the preset convergence condition is satisfied.

[0102] After obtaining the optimal Lagrange multiplier, the weight vector is calculated, and the formula is expressed as:

[0103] Wherein, represents the optimal Lagrange multiplier.

[0104] Select a support vector, and calculate the bias term. The formula is expressed as:

[0105] Wherein, represents the label of the k-th operating state, represents the k-th support vector.

[0106] The obtained support vector machine decision function is used to obtain the evaluation model. The support vector machine decision function formula is expressed as:

[0107] In the formula, sgn(z) represents the sign function. When z ≥ 0, sgn(z) = 1; when z < 0, sgn(z) = -1, and q represents a new sample.

[0108] The process of preliminarily adjusting the operation data according to the operation status according to preset rules includes: The operation status is divided into categories such as normal, slightly abnormal, moderately abnormal, and severely abnormal.

[0109] When the operation status is normal, keep the current operation data unchanged.

[0110] When the operation status is slightly abnormal, for example, if the operation speed is slightly lower than the normal range, increase the operation speed according to a preset ratio. If the conveyor belt tension is slightly small, appropriately increase the pressure of the tension adjusting device.

[0111] When the operation status is moderately abnormal, increase the adjustment intensity, such as increasing the operation speed by 10%, and at the same time monitor and finely adjust parameters such as the motor current.

[0112] When the operation status is severely abnormal, immediately stop the conveyor operation, issue an alarm, and conduct fault troubleshooting and repair.

[0113] The Kalman filter algorithm is used to fuse multi-dimensional data, and a long short-term memory network is used to construct an association relationship network for multi-dimensional data.

[0114] The process of using the Kalman filter algorithm to fuse multi-dimensional data includes: Comprehensively consider multi-dimensional information such as operation data, environmental data, and material data to determine the state vector that can describe the operation status of the workshop conveyor. For example, the state vector can include key parameters such as the speed and tension of the conveyor belt, and the current of the motor.

[0115] According to the physical characteristics and operation rules of the conveyor, establish a state transition equation to describe the relationship between the system states over time. Represent the state transition equation as a linear or non-linear mathematical model to reflect how the state at the current moment evolves to the state at the next moment.

[0116] Determine the observable multi-dimensional data, such as the operation speed, motor current, component temperature, etc. collected by various sensors.

[0117] Establish an observation equation to describe the relationship between the observation vector and the system state vector. This equation represents how the actual observed data is obtained from the system state.

[0118] According to the prior knowledge or initial measurement values of the system, estimate the initial state of the system to obtain the estimated value of the initial state vector.

[0119] Determine the covariance matrix of the initial state estimate, which reflects the uncertainty of the initial state estimate.

[0120] According to the state transition equation, use the state estimate value at the previous moment to predict the system state at the current moment.

[0121] According to the state transition equation and the initial covariance matrix, predict the covariance matrix of the state estimate at the current moment.

[0122] According to the predicted covariance matrix, the observation equation, and the observation noise covariance matrix, calculate the Kalman gain. The Kalman gain is used to balance the weights of the predicted value and the observed value in the state update.

[0123] Combine the observed value at the current moment and the predicted state, and use the Kalman gain to update the system state to obtain the optimal state estimate value at the current moment.

[0124] According to the Kalman gain and the predicted covariance matrix, update the covariance matrix of the state estimate to reflect the uncertainty of the updated state estimate.

[0125] As new observed data continuously arrives, continuously perform prediction and update operations to achieve real-time fusion of multi-dimensional data. Through continuous iteration, the Kalman filter algorithm can adaptively adjust the state estimate, reduce the influence of noise and uncertainty, and improve the accuracy and reliability of data fusion.

[0126] Take the system state estimate value fused by the Kalman filter algorithm as the final fusion result output. This result synthesizes the information of multi-dimensional data and can more accurately reflect the operating state of the workshop conveyor.

[0127] The process of constructing the correlation relationship network of multi-dimensional data using the long short-term memory network includes: Take the multi-dimensional data fused by the Kalman filter as the input of the long short-term memory network. Let the input sequence be x1, x2, …, x T , where x t represents the multi-dimensional data vector at time t.

[0128] Set the structure of the long short-term memory network, including the input layer, hidden layer, and output layer. The input layer is used to receive the input sequence. The hidden layer contains multiple long short-term memory network units, which are used to capture the long-term dependence relationships in the input sequence. The output layer is used to output the hidden states of each multi-dimensional data in the input sequence.

[0129] Train the long short-term memory network to analyze the time series correlation relationships between each multi-dimensional data.

[0130] Taking the hidden state as a node and the connection weights between nodes representing the association strength between data, an association relationship network of multi-dimensional data is obtained.

[0131] Based on the association relationship network, a multi-objective optimization model integrating transportation efficiency, energy consumption, and equipment wear is established. The multi-objective optimization model is solved using a multi-objective evolutionary algorithm to obtain a solution set of adjustment strategies, and the optimal adjustment strategy for the current working condition is selected through fuzzy decision-making theory.

[0132] The process of establishing a multi-objective optimization model integrating transportation efficiency, energy consumption, and equipment wear based on the association relationship network includes: Define the transportation efficiency as the ratio of the weight of the conveyed material per unit time to the maximum transportation capacity. Calculate the transportation efficiency based on the weight of the conveyed material per unit time and the maximum transportation capacity of the conveyor. The formula is expressed as:

[0133] In the formula, represents the transportation efficiency, represents the weight of the conveyed material per unit time, and M represents the maximum transportation capacity.

[0134] Define the energy consumption as the power consumption of the motor. Calculate the energy consumption based on the motor power and the running time. The formula is expressed as:

[0135] In the formula, represents the energy consumption, P represents the motor power, and t represents the running time.

[0136] Establish a wear model based on the change in conveyor belt tension and motor load. The formula is expressed as:

[0137] In the formula, represents equipment wear, represents the change in conveyor belt tension, represents the change in motor current, and represent the weight coefficients.

[0138] Based on the transportation efficiency, energy consumption, and equipment wear, establish a comprehensive objective function as the multi-objective optimization model. The formula of the comprehensive objective function is expressed as:

[0139] In the formula, x represents the operating data vector.

[0140] The process of using a multi-objective evolutionary algorithm to solve the multi-objective optimization model to obtain a solution set of adjustment strategies includes: Randomly generate a certain number of individuals as the initial population, and the individuals represent the operation data vectors.

[0141] For each individual, calculate its comprehensive objective function value F(x).

[0142] Use the non-dominated sorting and crowding distance sorting methods to select excellent individuals to enter the next generation.

[0143] Perform crossover and mutation operations on the selected individuals to generate new individuals.

[0144] Merge the newly generated individuals with the original population, and perform non-dominated sorting and crowding distance sorting again to select a certain number of individuals to form the next generation population.

[0145] When the preset termination condition is met, use the individuals in the current population as the solution set of the adjustment strategy.

[0146] The process of selecting the optimal adjustment strategy for the current working condition through the fuzzy decision theory includes: Determine the factor set and the evaluation set. The factor set U = {u1, u2, u3}, where u1, u2, and u3 correspond to the conveying efficiency, energy consumption, and equipment wear respectively. The evaluation set V = {v1, v2,..., v n}, v i represents the quality level of the adjustment strategy.

[0147] For each factor u i , determine its membership function according to the performance of each strategy in the adjustment strategy solution set under this factor, and obtain the fuzzy relation matrix , where r ij represents the membership degree of the i-th factor to the j-th strategy.

[0148] According to the requirements of the current working condition, determine the weight vector of each factor , where, and , represents the i-th weight vector.

[0149] Calculate the fuzzy comprehensive evaluation vector B = A·R, where · represents the fuzzy composition operator.

[0150] According to the values of the elements in the fuzzy comprehensive evaluation vector B, select the adjustment strategy corresponding to the element with the largest membership degree as the optimal adjustment strategy for the current working condition.

[0151] Using servo drive and variable frequency speed regulation technology, convert the optimal adjustment strategy into control instructions through a programmable logic controller, and combine feedforward and feedback control to adjust the operation data. The process includes: Receive the optimal adjustment strategy through the programmable logic controller, and extract the key adjustment parameters in the optimal adjustment strategy.

[0152] The programmable logic controller receives from the system the optimal adjustment strategy for the current working condition selected by the fuzzy decision theory. This strategy includes specific adjustment parameters and targets for the operation data of the workshop conveyor, such as conveying speed, power, material feeding amount, etc.

[0153] The programmable logic controller analyzes the optimal adjustment strategy and extracts the key adjustment parameters and target values therein. For example, if the adjustment strategy requires increasing the running speed of the conveyor from the current 50 meters per minute to 60 meters per minute, the programmable logic controller can identify the speed adjustment information.

[0154] According to the physical characteristics and historical operation data of the workshop conveyor, a feedforward control model is established. This model describes the relationship between input variables (such as parameters in the adjustment strategy) and output variables (such as the running state of the conveyor). For example, through experiments and data analysis, the functional relationship between the speed of the conveyor and the input voltage of the motor is determined.

[0155] Using the feedforward control model, according to the optimal adjustment strategy parameters obtained by analysis, the corresponding feedforward control instructions are calculated. Taking the aforementioned speed adjustment as an example, according to the functional relationship between speed and motor input voltage, the value of the motor input voltage required to increase the conveyor speed to 60 meters per minute is calculated.

[0156] The programmable logic controller sends the calculated feedforward control instructions to the servo drive and variable frequency speed regulation equipment to adjust the operation of the conveyor in advance, reducing the response time and error.

[0157] In summary, this embodiment provides an automatic adjustment method for a workshop conveyor. By collecting multi-dimensional data in real time and performing denoising, feature extraction, and state evaluation, abnormal situations during the operation of the conveyor can be detected in a timely manner. For example, sudden changes in motor current and abnormal increases in component temperature can be accurately captured. Once an anomaly is detected, the system will quickly adjust the initial operation data according to preset rules, promptly correct possible problems, prevent the failure from deteriorating further, thereby ensuring the continuous and stable operation of the conveyor and reducing production interruptions caused by equipment failures.

[0158] The data correlation network constructed by the long short-term memory network can deeply explore the internal connections between multi-dimensional data. Combining the multi-objective optimization model and the fuzzy decision theory, the operation parameters of the conveyor, such as running speed, conveyor belt tension, etc., can be dynamically adjusted according to factors such as the current material characteristics and environmental conditions, enabling the conveyor to operate in an optimal state, quickly and efficiently complete the material conveying task, and greatly improving the production efficiency.

[0159] Through a multi-objective optimization model that comprehensively considers transportation efficiency, energy consumption, and equipment wear, it is possible to minimize the energy consumption of the conveyor while ensuring transportation efficiency. By precisely adjusting the operating parameters, unnecessary energy waste is avoided, achieving a balance between energy conservation and high efficiency. At the same time, reasonable adjustment of operating parameters can also reduce equipment wear, extend the service life of the equipment, and reduce equipment maintenance costs and replacement frequencies.

[0160] Based on the same general inventive concept, the present invention also protects an automatic adjustment system for a workshop conveyor. The following describes an automatic adjustment system for a workshop conveyor provided by the present invention. The automatic adjustment system for a workshop conveyor described below can be mutually referred to in correspondence with the automatic adjustment method for a workshop conveyor described above.

[0161] Figure 2 It is a schematic structural diagram of an automatic adjustment system for a workshop conveyor provided by an embodiment of the present invention.

[0162] As Figure 2 shown, an automatic adjustment system for a workshop conveyor includes a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor includes a data acquisition module, a feature extraction module, a preliminary adjustment module, a correlation relationship construction module, a regulation strategy generation module, and a control adjustment module.

[0163] The data acquisition module is used to collect multi-dimensional data of the workshop conveyor in real time. The multi-dimensional data includes operation data, environmental data, and material data.

[0164] The feature extraction module is used to denoise the multi-dimensions using the wavelet transform method and perform feature extraction using principal component analysis to obtain operation features, environmental features, and material features.

[0165] The preliminary adjustment module is used to construct an evaluation model based on a support vector machine, evaluate the operating state of the workshop conveyor in real time according to the operation features, environmental features, and material features, and perform preliminary adjustment of the operation data according to the operating state according to preset rules.

[0166] The correlation relationship construction module is used to fuse multi-dimensional data using the Kalman filter algorithm and construct a correlation relationship network of multi-dimensional data using a long short-term memory network.

[0167] The regulation strategy generation module is used to establish a multi-objective optimization model that comprehensively considers transportation efficiency, energy consumption, and equipment wear based on the correlation relationship network, solve the multi-objective optimization model using a multi-objective evolutionary algorithm to obtain a set of regulation strategies, and select the optimal regulation strategy for the current working condition through fuzzy decision theory.

[0168] The control and regulation module is used to utilize servo drive and variable frequency speed regulation technologies to convert the optimal regulation strategy into control instructions through a programmable logic controller, and combine feedforward and feedback control to regulate the operation data.

[0169] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0170] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic adjustment method for a workshop conveyor, characterized in that, Including: Collecting multi-dimensional data of the workshop conveyor in real time, where the multi-dimensional data includes operation data, environmental data, and material data; Using the wavelet transform method to denoise the multi-dimensional data, and adopting principal component analysis for feature extraction to obtain operation features, environmental features, and material features; Constructing an evaluation model based on support vector machines, and according to the operation features, environmental features, and material features, evaluating the operation state of the workshop conveyor in real time, and adjusting the initial operation data according to the operation state according to preset rules; Adopting the Kalman filter algorithm to fuse the multi-dimensional data, and using the long short-term memory network to construct the correlation network of the multi-dimensional data; Establishing a multi-objective optimization model for comprehensive conveying efficiency, energy consumption, and equipment wear according to the correlation network, using the multi-objective evolutionary algorithm to solve the multi-objective optimization model to obtain a solution set of adjustment strategies, and selecting the optimal adjustment strategy for the current working condition through the fuzzy decision-making theory; Utilizing servo drive and variable frequency speed regulation technologies, converting the optimal adjustment strategy into a control instruction through a programmable logic controller, and combining feedforward and feedback control to adjust the operation data.

2. The automatic adjustment method for a workshop conveyor according to claim 1, characterized in that, The operation data includes operation speed, motor current, conveyor belt tension, and the rotation speed of the conveyor rotating components; the environmental data includes the temperature of the conveyor components and the operation sound; the material data includes the weight, volume, shape, density, and distribution of the materials.

3. The automatic adjustment method for a workshop conveyor according to claim 1, characterized in that The process of adopting principal component analysis for feature extraction includes: Constructing a multi-dimensional data matrix, and for each feature in the multi-dimensional data matrix, calculating its mean and standard deviation to obtain the standardized data and the covariance matrix; Performing eigenvalue decomposition on the covariance matrix, and according to the size of the eigenvalues, selecting the eigenvectors corresponding to the top k largest eigenvalues as the principal components to obtain the operation features, environmental features, and material features.

4. The automatic adjustment method for a workshop conveyor according to claim 1, characterized in that, The process of constructing an evaluation model based on support vector machines includes: Collect multi-dimensional data samples of the historical working conditions of the collecting conveyor. Suppose there are s samples of the collected historical data, and each sample contains g features, which are represented as a feature matrix , where is the feature vector of the i-th sample, and the corresponding operating status label is ; Defining a Gaussian kernel function, which is expressed by the formula: In the formula, and represent the feature vectors of the i-th sample and the j-th sample, represents the square of the Euclidean distance between the i-th sample and the j-th sample, represents the bandwidth parameter of the Gaussian kernel; Introducing slack variables to construct an optimization problem, which is expressed by the formula: where \(w\) represents the weight vector, and \(b\) is the bias term. denotes the vector after mapping to a high-dimensional space, \(C\) represents the penalty parameter, denotes the \(i\)-th operating state label, Converting the optimization problem into a dual problem, using the sequential minimal optimization algorithm to solve the dual problem, calculating the weight vector and the bias term, and obtaining the evaluation model.

5. The automatic adjustment method for a workshop conveyor according to claim 1, characterized in that, The process of using the long short-term memory network to construct the correlation network of the multi-dimensional data includes: Taking the multi-dimensional data fused by the Kalman filter as the input of the long short-term memory network to obtain an input sequence; Setting the structure of the long short-term memory network, including an input layer, a hidden layer, and an output layer; the input layer is used to receive the input sequence; the hidden layer contains multiple long short-term memory network units, which are used to capture the long-term dependence relationships in the input sequence; the output layer is used to output the hidden states of each multi-dimensional data in the input sequence; Training the long short-term memory network to analyze the time series correlation relationships between each multi-dimensional data; Taking the hidden states as nodes, and the connection weights between the nodes represent the correlation strength between the data, to obtain the correlation network of the multi-dimensional data.

6. The automatic adjustment method for a workshop conveyor according to claim 1, characterized in that, The process of establishing a multi-objective optimization model for comprehensive conveying efficiency, energy consumption, and equipment wear according to the correlation network includes: Define the conveying efficiency as the ratio of the weight of the conveyed material per unit time to the maximum conveying capacity, and calculate the conveying efficiency according to the weight of the conveyed material per unit time and the maximum conveying capacity of the conveyor; Define the energy consumption as the power consumption of the motor, and calculate the energy consumption according to the motor power and the running time; Establish a wear model based on the tension change of the conveyor belt and the motor load; Establish a comprehensive objective function as a multi-objective optimization model according to the conveying efficiency, energy consumption and equipment wear; 7. The automatic adjustment method for a workshop conveyor according to claim 1, characterized in that, The process of using a multi-objective evolutionary algorithm to solve the multi-objective optimization model and obtain the solution set of adjustment strategies includes: Randomly generate a certain number of individuals as the initial population, and the individuals represent the operation data vectors; For each individual, calculate its comprehensive objective function value; Use the methods of non-dominated sorting and crowding distance sorting to select excellent individuals to enter the next generation; Perform crossover and mutation operations on the selected individuals to generate new individuals; Merge the newly generated individuals with the original population, perform non-dominated sorting and crowding distance sorting again, and select a certain number of individuals to form the next generation population; When the preset termination condition is met, use the individuals in the current population as the solution set of adjustment strategies.

8. The automatic adjustment method for a workshop conveyor according to claim 1, wherein The process of selecting the optimal adjustment strategy for the current working condition through the fuzzy decision-making theory includes: Determine the factor set and the evaluation set. The factors in the factor set respectively correspond to the conveying efficiency, energy consumption and equipment wear; the evaluations in the evaluation set represent the quality levels of the adjustment strategies; For each factor, determine its membership function according to the performance of each strategy in the adjustment strategy solution set under this factor, and obtain the fuzzy relation matrix; According to the requirements of the current working condition, determine the weight vector of each factor; Calculate the fuzzy comprehensive evaluation vector, and select the adjustment strategy corresponding to the element with the largest membership degree as the optimal adjustment strategy for the current working condition according to the values of the elements in the fuzzy comprehensive evaluation vector.

9. The automatic adjustment method for a workshop conveyor according to claim 1, wherein, The process of combining feedforward and feedback control to adjust the operation data includes: Receive the optimal adjustment strategy through the programmable logic controller, and extract the key adjustment parameters in the optimal adjustment strategy; Establish a feedforward control model according to the physical characteristics and historical operation data of the workshop conveyor; Use the feedforward control model to calculate the corresponding feedforward control instruction according to the key adjustment parameters; Send the feedforward control instruction to the servo drive and the variable frequency speed regulation equipment to adjust the operation data of the conveyor.

10. An automatic adjustment system for a workshop conveyor, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements an automatic adjustment method for a workshop conveyor as described in any one of claims 1 to 9.

Images