Energy consumption monitoring optimization method for energy-saving circulating cold oil press

Abstract

The invention belongs to the technical field of circulating cold oil press energy consumption monitoring, and particularly relates to an energy-saving circulating cold oil press energy consumption monitoring optimization method which comprises the following steps: S1, constructing an energy consumption monitoring system; s2, establishing an energy consumption analysis model; s3, performing real-time energy consumption monitoring and alarming; s4, generating and implementing an optimization method; according to the energy consumption analysis model, under different material processing requirements, the optimal operation parameter combination is solved through an optimization algorithm. According to the integral structure provided by the embodiment of the invention, the energy consumption of the cold press is accurately monitored in real time, the energy consumption is reduced by more than 50% through intelligent optimization, the service life of equipment is prolonged, and the production benefit is improved; by means of the deep learning neural network, the energy consumption of the cold press can be accurately predicted, errors are controlled within an extremely small range, the energy utilization efficiency of the cold press is effectively improved, the operation cost of an enterprise is reduced, and the market competitiveness of cold-pressed products is enhanced; the particle swarm optimization algorithm is utilized to quickly adapt to the working condition change of the cold press, and the operation parameters are accurately optimized.

Description

Technical Field

[0001] The present application relates to the technical field of energy consumption monitoring of circulating cold-pressing oil machines, and in particular to an energy-saving circulating cold-pressing oil machine energy consumption monitoring optimization method. Background Art

[0002] The pressing of vegetable oil can be divided into hot pressing and cold pressing. The crude oil produced by hot pressing has been leached and refined, which will cause solvent residues and most of the fat-soluble vitamins will be lost. The oil produced by cold pressing has pure natural characteristics, avoiding the production of trans fatty acids by high-temperature processing of oils and fats, which can easily lead to cardiovascular diseases, oil polymers and other harmful substances, and retains the physiologically active substances in the oil, such as vitamin E, sterols, γ-linolenic acid and functional food pigments and other beneficial substances;

[0003] Cold pressing is a production process for oil. Cold pressing generally requires processing at an environment below 60°C to retain the most complete nutrients.

[0004] When the circulating cold press oil machine is in use, its energy consumption is affected by many factors such as raw material characteristics, equipment parameters, and operating procedures. The traditional energy consumption control method lacks dynamic adaptability and is difficult to adjust in real time according to working conditions, resulting in low energy utilization efficiency and increased production costs. Therefore, we proposed an energy-saving circulating cold press oil machine energy consumption monitoring and optimization method. Summary of the invention

[0005] The present application provides an energy-saving circulating cold press energy consumption monitoring and optimization method to solve the above-mentioned problems.

[0006] The present application provides an energy-saving type circulating cold press oil machine energy consumption monitoring optimization method, including the following method:

[0007] S1. Construction of energy consumption monitoring system;

[0008] High-precision data collection sensors and energy consumption monitors are installed on the energy-consuming parts of the motor, hydraulic pump, and cooling device of the circulating cold press to collect operating data in real time. The collected analog signals are converted into digital signals through the A / D conversion module and transmitted to the data acquisition card, which is then processed by the embedded microprocessor and sent to the monitoring terminal through the wireless communication module.

[0009] S2, energy consumption analysis model establishment;

[0010] Based on the energy consumption data of the circulating cold press oil machine and the corresponding working condition data in the big data, the energy consumption prediction model is constructed using the learning algorithm built in the monitoring terminal. The high-precision acquisition sensor of the circulating cold press oil machine is used as the input variable, and the energy consumption value monitored by the energy consumption monitor is used as the output variable. Through continuous training and optimization of the learning algorithm, it can accurately reflect the relationship between energy consumption and working conditions.

[0011] S3, real-time energy consumption monitoring and alarm;

[0012] The monitoring terminal displays the energy consumption of each component of the circulating cold press, the total energy consumption and the energy consumption trend curve in real time, and sets the energy consumption threshold. When the real-time energy consumption exceeds the threshold, the sound and light alarm is triggered immediately;

[0013] S4, optimization method generation and implementation;

[0014] According to the energy consumption analysis model, the optimization algorithm is used to solve the best operating parameter combination under different material processing requirements.

[0015] Preferably, the high-precision acquisition sensor includes a current transformer, a pressure sensor, a speed sensor, a humidity sensor and a flow rate sensor, and the current transformer, pressure sensor, speed sensor, humidity sensor and flow rate sensor respectively monitor the power consumption, chamber pressure, screw speed, material humidity and cooling water flow rate of the circulating cold press.

[0016] Preferably, the learning algorithm adopts a deep learning neural network.

[0017] Preferably, the optimization algorithm adopts a particle swarm optimization algorithm.

[0018] Preferably, the energy consumption analysis model establishment further includes:

[0019] S21, data collection and preprocessing;

[0020] The data collected by high-precision acquisition sensors and energy consumption monitors are normalized and preprocessed by outlier removal to remove noise interference so that the data meets the neural network input requirements;

[0021] S22, neural network architecture construction;

[0022] Construct a deep learning neural network based on a multi-layer perceptron, including input layer, hidden layer and output layer;

[0023] S23, model training and optimization;

[0024] The large amount of circulating cold press operation data stored in the monitoring terminal is divided into training set, validation set and test set according to the set ratio. The back propagation algorithm is used to train the neural network with the mean square error as the loss function. According to the accuracy of the validation set and the loss value feedback information, the variant optimization algorithm is used to dynamically adjust the weights of the neural network to make the model converge to the optimal solution.

[0025] Preferably, the input layer node receives various pre-processed working condition data and energy consumption data features;

[0026] The hidden layer is multiple, each hidden layer uses a different number of neurons, and the neuron activation function uses the ReLU function to enhance the nonlinear expression ability of the model and deeply mine the intrinsic correlation of the data in a layer-by-layer progressive manner;

[0027] The output layer sets one or more nodes for predicting the real-time energy consumption of the cold press, the optimal operating parameter combination or the abnormal energy consumption warning signal.

[0028] Preferably, the optimization method generation and implementation further includes:

[0029] S31, particle swarm model construction;

[0030] The power consumption, chamber pressure, screw speed, material humidity and cooling water flow rate parameters of the circulating cold press are set as particle dimensions. Each particle represents a possible combination of operating parameters. A group of particles are initialized and their initial positions and speeds in each dimension are randomly assigned. The position corresponds to the specific parameter value, and the speed determines the speed and direction of particle movement.

[0031] S32, fitness function setting;

[0032] The fitness function is constructed with the total energy consumption of the circulating cold press as the core. The parameter values ​​represented by the particles are substituted into the energy consumption calculation model by comprehensively considering the quality indicators of the oil products, and the unit product energy consumption is obtained. The lower the energy consumption and the higher the product quality, the higher the fitness, which is used to measure the quality of the particles.

[0033] S33, iterative optimization process;

[0034] In each round of iteration, particles update their speed and position based on their own optimal position and the group's optimal position. The position is updated based on the new speed. After the update, the fitness is recalculated and iterated continuously, so that the particles continue to move to the parameter area with lower energy consumption and better quality.

[0035] S34, model training and optimization;

[0036] After iterating to the preset number of times or reaching a satisfactory energy consumption optimization target, the optimal particle in the swarm is selected, and the parameter value represented by it is applied to the actual operation of the circulating cold press oil machine. The energy consumption and product quality changes are monitored in real time. According to the feedback information, the particle swarm optimization algorithm parameters are fine-tuned or some particles are reinitialized to start a new round of optimization and continuously improve the energy efficiency of the cold press operation.

[0037] Preferably, the energy consumption calculation model formula is P=H·K·S·V, wherein: H represents the parameter value represented by the particle, K represents the power of the circulating cold press oil machine, S represents the usage time of the circulating cold press oil machine, and V represents the depreciation coefficient of the circulating cold press oil machine.

[0038] Preferably, the oil product quality indicators include oil yield and meal residual oil rate.

[0039] Preferably, the optimization algorithm solves the best operating parameter combination including the optimal screw speed range, the optimal cooling water volume, and the reasonable start and stop time of the hydraulic pump.

[0040] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0041] The overall structure provided by the embodiment of the present application realizes real-time and accurate monitoring of the energy consumption of the cold press, reduces energy consumption by more than 50% through intelligent optimization, prolongs the service life of the equipment, and improves production efficiency;

[0042] With the help of deep learning neural network, the energy consumption of cold press can be accurately predicted, and the error can be controlled within a very small range, which can effectively improve the energy utilization efficiency of cold press, reduce enterprise operating costs, and enhance the market competitiveness of cold press products;

[0043] The particle swarm optimization algorithm can quickly adapt to changes in the operating conditions of the cold press, accurately optimize operating parameters, and improve product quality indicators such as oil yield, providing an effective way to save energy and reduce consumption and improve efficiency in the cold press industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] Figure 1 It is the overall principle flow chart of the present invention;

[0047] Figure 2 Establishing a flow chart for the energy consumption analysis model of the present invention;

[0048] Figure 3 The present invention is a flowchart for the production and implementation of the optimization method. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0050] Various embodiments of the present application may exist in the form of a range. It should be understood that the description in the form of a range is only for convenience and simplicity and should not be understood as a hard limit to the scope of the present application; therefore, it should be considered that the range description has specifically disclosed all possible sub-ranges and single values ​​within the range. For example, it should be considered that the range description from 1 to 6 has specifically disclosed sub-ranges, such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6, etc., as well as single numbers within the range, such as 1, 2, 3, 4, 5 and 6, which are applicable regardless of the range. In addition, whenever a numerical range is indicated in the present application, it is meant to include any quoted numbers (fractions or integers) within the indicated range. Unless otherwise specified, various raw materials, reagents, instruments and equipment used in the present application, etc., can be purchased from the market or can be prepared by existing equipment.

[0051] In the present application, in the absence of any contrary description, the directional words used, such as "upper" and "lower", are specifically the directions of the drawings in the accompanying drawings. In addition, in the present application, the terms "include", "comprise", etc. refer to "including but not limited to". In the present application, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. In the present application, "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. Wherein A, B can be singular or plural. In the present application, "at least one" refers to one or more, and "plural" refers to two or more. "At least one", "at least one of the following" or similar expressions refer to any combination of these items, including any combination of singular items or plural items. For example, "at least one of a, b, or c" or "at least one of a, b and c" can both mean: a, b, c, ab, i.e. a and b, ac, bc or abc, where a, b, c can be single or plural, respectively.

[0052] like Figure 1 and Figure 3As shown: The embodiment of the present application provides an energy-saving type circulating cold press oil machine energy consumption monitoring optimization method, including the following method:

[0053] S1. Construction of energy consumption monitoring system;

[0054] High-precision data collection sensors and energy consumption monitors are installed on the energy-consuming parts of the motor, hydraulic pump, and cooling device of the circulating cold press to collect operating data in real time. The collected analog signals are converted into digital signals through the A / D conversion module and transmitted to the data acquisition card, which is then processed by the embedded microprocessor and sent to the monitoring terminal through the wireless communication module.

[0055] S2, energy consumption analysis model establishment;

[0056] Based on the energy consumption data of the circulating cold press oil machine and the corresponding working condition data in the big data, the energy consumption prediction model is constructed using the learning algorithm built in the monitoring terminal. The high-precision acquisition sensor of the circulating cold press oil machine is used as the input variable, and the energy consumption value monitored by the energy consumption monitor is used as the output variable. Through continuous training and optimization of the learning algorithm, it can accurately reflect the relationship between energy consumption and working conditions.

[0057] S3, real-time energy consumption monitoring and alarm;

[0058] The monitoring terminal displays the energy consumption of each component of the circulating cold press, the total energy consumption and the energy consumption trend curve in real time, and sets the energy consumption threshold. When the real-time energy consumption exceeds the threshold, the sound and light alarm is triggered immediately;

[0059] S4, optimization method generation and implementation;

[0060] According to the energy consumption analysis model, the optimization algorithm is used to solve the best operating parameter combination under different material processing requirements.

[0061] The high-precision acquisition sensor includes a current transformer, a pressure sensor, a speed sensor, a humidity sensor and a flow rate sensor. The current transformer, pressure sensor, speed sensor, humidity sensor and flow rate sensor respectively monitor the power consumption, chamber pressure, screw speed, material humidity and cooling water flow rate of the circulating cold press.

[0062] The learning algorithm uses a deep learning neural network.

[0063] The optimization algorithm adopts particle swarm optimization algorithm.

[0064] The energy consumption analysis model establishment also includes:

[0065] S21, data collection and preprocessing;

[0066] The data collected by high-precision acquisition sensors and energy consumption monitors are normalized and preprocessed by outlier removal to remove noise interference so that the data meets the neural network input requirements;

[0067] S22, neural network architecture construction;

[0068] Construct a deep learning neural network based on a multi-layer perceptron, including input layer, hidden layer and output layer;

[0069] S23, model training and optimization;

[0070] The large amount of circulating cold press operation data stored in the monitoring terminal is divided into training set, validation set and test set according to the set ratio. The back propagation algorithm is used to train the neural network with the mean square error as the loss function. According to the accuracy of the validation set and the loss value feedback information, the variant optimization algorithm is used to dynamically adjust the weights of the neural network to make the model converge to the optimal solution.

[0071] The input layer node receives various pre-processed working condition data and energy consumption data features;

[0072] The hidden layer is multiple, each hidden layer uses a different number of neurons, and the neuron activation function uses the ReLU function to enhance the nonlinear expression ability of the model and deeply mine the intrinsic correlation of the data in a layer-by-layer progressive manner;

[0073] The output layer sets one or more nodes for predicting the real-time energy consumption of the cold press, the optimal operating parameter combination or the abnormal energy consumption warning signal.

[0074] The optimization method generation and implementation also includes:

[0075] S31, particle swarm model construction;

[0076] The power consumption, chamber pressure, screw speed, material humidity and cooling water flow rate parameters of the circulating cold press are set as particle dimensions. Each particle represents a possible combination of operating parameters. A group of particles are initialized and their initial positions and speeds in each dimension are randomly assigned. The position corresponds to the specific parameter value, and the speed determines the speed and direction of particle movement.

[0077] S32, fitness function setting;

[0078] The fitness function is constructed with the total energy consumption of the circulating cold press as the core. The parameter values ​​represented by the particles are substituted into the energy consumption calculation model by comprehensively considering the quality indicators of the oil products, and the unit product energy consumption is obtained. The lower the energy consumption and the higher the product quality, the higher the fitness, which is used to measure the quality of the particles.

[0079] S33, iterative optimization process;

[0080] In each round of iteration, particles update their speed and position based on their own optimal position and the group's optimal position. The position is updated based on the new speed. After the update, the fitness is recalculated and iterated continuously, so that the particles continue to move to the parameter area with lower energy consumption and better quality.

[0081] S34, model training and optimization;

[0082] After iterating to the preset number of times or reaching a satisfactory energy consumption optimization target, the optimal particle in the swarm is selected, and the parameter value represented by it is applied to the actual operation of the circulating cold press oil machine. The energy consumption and product quality changes are monitored in real time. According to the feedback information, the particle swarm optimization algorithm parameters are fine-tuned or some particles are reinitialized to start a new round of optimization and continuously improve the energy efficiency of the cold press operation.

[0083] The energy consumption calculation model formula is P=H·K·S·V, wherein: H represents the parameter value represented by the particle, K represents the power of the circulating cold press oil machine, S represents the use time of the circulating cold press oil machine, and V represents the depreciation coefficient of the circulating cold press oil machine.

[0084] The oil product quality indicators include oil yield and meal residual oil rate.

[0085] The optimization algorithm solves the best operating parameter combination including the optimal screw speed range, the optimal cooling water volume, and the reasonable start and stop time of the hydraulic pump.

[0086] During the assembly stage of the circulating cold press, the high-precision acquisition sensor, A / D conversion module, data acquisition card, embedded microprocessor, wireless communication module and monitoring terminal are correctly installed according to the electrical connection diagram, each component is debugged to normal working state, and the high-precision acquisition sensor is calibrated to ensure the accuracy of the collected data;

[0087] The circulating cold press oil machine was tested for at least 72 hours, and energy consumption and operating condition data were continuously collected. The data were divided into training set and test set in a ratio of 7:3. The energy consumption prediction model was trained with the training set, and the model accuracy was verified with the test set. The model structure and parameters were repeatedly adjusted to meet the preset accuracy requirements.

[0088] During formal production, the monitoring terminal updates the energy consumption data every 3 hours. According to the energy consumption analysis model and optimization strategy, the operator adjusts the parameters of the cold press in a timely manner; the equipment maintenance personnel perform regular maintenance according to the prompts of the monitoring terminal and record the maintenance status in the equipment file to provide a reference for subsequent optimization.

[0089] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. It will be apparent to those skilled in the art that various modifications to these embodiments are possible, and the general principles defined in the present application can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown in the present application, but will conform to the widest scope consistent with the principles and novel features applied for by the present application.

Claims

1. An energy-saving circulating cold press oil machine energy consumption monitoring and optimization method, characterized in that: The following methods are included: S1. Construction of energy consumption monitoring system; High-precision data collection sensors and energy consumption monitors are installed on the energy-consuming parts of the motor, hydraulic pump, and cooling device of the circulating cold press to collect operating data in real time. The collected analog signals are converted into digital signals through the A / D conversion module and transmitted to the data acquisition card, which is then processed by the embedded microprocessor and sent to the monitoring terminal through the wireless communication module. S2, energy consumption analysis model establishment; Based on the energy consumption data of the circulating cold press oil machine and the corresponding working condition data in the big data, the energy consumption prediction model is constructed using the learning algorithm built in the monitoring terminal. The high-precision acquisition sensor of the circulating cold press oil machine is used as the input variable, and the energy consumption value monitored by the energy consumption monitor is used as the output variable. Through continuous training and optimization of the learning algorithm, it can accurately reflect the relationship between energy consumption and working conditions. S3, real-time energy consumption monitoring and alarm; The monitoring terminal displays the energy consumption of each component of the circulating cold press in real time, the total energy consumption and the energy consumption trend curve, and sets the energy consumption threshold. When the real-time energy consumption exceeds the threshold, the sound and light alarm is immediately triggered; S4, optimization method generation and implementation; According to the energy consumption analysis model, the optimization algorithm is used to solve the best operating parameter combination under different material processing requirements.

2. The energy consumption monitoring and optimization method of an energy-saving circulating cold press oil press according to claim 1 is characterized in that: The high-precision acquisition sensor includes a current transformer, a pressure sensor, a speed sensor, a humidity sensor and a flow rate sensor. The current transformer, pressure sensor, speed sensor, humidity sensor and flow rate sensor respectively monitor the power consumption, chamber pressure, screw speed, material humidity and cooling water flow rate of the circulating cold press.

3. The energy consumption monitoring and optimization method of an energy-saving circulating cold press oil press according to claim 1 is characterized in that: The learning algorithm uses a deep learning neural network.

4. The energy consumption monitoring and optimization method of an energy-saving circulating cold press oil press according to claim 1 is characterized in that: The optimization algorithm adopts particle swarm optimization algorithm.

5. The energy consumption monitoring and optimization method of an energy-saving circulating cold press oil press according to claim 1 is characterized in that: The energy consumption analysis model establishment also includes: S21, data collection and preprocessing; The data collected by high-precision acquisition sensors and energy consumption monitors are normalized and preprocessed by outlier removal to remove noise interference so that the data meets the neural network input requirements; S22, neural network architecture construction; Construct a deep learning neural network based on a multi-layer perceptron, including input layer, hidden layer and output layer; S23, model training and optimization; The large amount of circulating cold press operation data stored in the monitoring terminal is divided into training set, validation set and test set according to the set ratio. The back propagation algorithm is used to train the neural network with the mean square error as the loss function. According to the accuracy of the validation set and the loss value feedback information, the variant optimization algorithm is used to dynamically adjust the weights of the neural network to make the model converge to the optimal solution.

6. The energy consumption monitoring and optimization method of an energy-saving circulating cold press oil press according to claim 5 is characterized in that: The input layer node receives various pre-processed working condition data and energy consumption data features; The hidden layer is multiple, each hidden layer uses a different number of neurons, and the neuron activation function uses the ReLU function to enhance the nonlinear expression ability of the model and deeply mine the intrinsic correlation of the data in a layer-by-layer progressive manner; The output layer sets one or more nodes for predicting the real-time energy consumption of the cold press, the optimal operating parameter combination or the abnormal energy consumption warning signal.

7. The energy consumption monitoring and optimization method of an energy-saving circulating cold press oil press according to claim 1 is characterized in that: The optimization method generation and implementation also includes: S31, particle swarm model construction; The power consumption, chamber pressure, screw speed, material humidity and cooling water flow rate parameters of the circulating cold press are set as particle dimensions. Each particle represents a possible combination of operating parameters. A group of particles are initialized and their initial positions and speeds in each dimension are randomly assigned. The position corresponds to the specific parameter value, and the speed determines the speed and direction of particle movement. S32, fitness function setting; The fitness function is constructed with the total energy consumption of the circulating cold press as the core. The parameter values ​​represented by the particles are substituted into the energy consumption calculation model by comprehensively considering the quality indicators of the oil products, and the unit product energy consumption is obtained. The lower the energy consumption and the higher the product quality, the higher the fitness, which is used to measure the quality of the particles. S33, iterative optimization process; In each round of iteration, particles update their speed and position based on their own optimal position and the group's optimal position. The position is updated based on the new speed. After the update, the fitness is recalculated and iterated continuously, so that the particles continue to move to the parameter area with lower energy consumption and better quality. S34, model training and optimization; After iterating to the preset number of times or reaching a satisfactory energy consumption optimization target, the optimal particle in the swarm is selected, and the parameter value represented by it is applied to the actual operation of the circulating cold press oil machine. The energy consumption and product quality changes are monitored in real time. According to the feedback information, the particle swarm optimization algorithm parameters are fine-tuned or some particles are reinitialized to start a new round of optimization and continuously improve the energy efficiency of the cold press operation.

8. The energy consumption monitoring and optimization method of an energy-saving circulating cold press oil press according to claim 7 is characterized in that: The energy consumption calculation model formula is P=H·K·S·V, wherein: H represents the parameter value represented by the particle, K represents the power of the circulating cold press oil machine, S represents the use time of the circulating cold press oil machine, and V represents the depreciation coefficient of the circulating cold press oil machine.

9. The energy consumption monitoring and optimization method of an energy-saving circulating cold press oil press according to claim 7 is characterized in that: The oil product quality indicators include oil yield and meal residual oil rate.

10. The energy consumption monitoring and optimization method of an energy-saving circulating cold press oil press according to claim 1 is characterized in that: The optimization algorithm solves the best operating parameter combination including the optimal screw speed range, the optimal cooling water volume, and the reasonable start and stop time of the hydraulic pump.

Images