Workshop conveyor automatic adjusting method and system based on material conveying data

Abstract

The invention discloses a workshop conveyor automatic adjusting method and system based on material conveying data, and relates to the technical field of workshop conveyors, and the method comprises the following steps: constructing a multi-modal data set based on the collected material conveying data, and processing the multi-modal data set through a multi-modal deep learning network to obtain multi-dimensional conveying features; setting constraint rules according to the operation parameters and historical data of the workshop conveyors, and dividing operation modes of the workshop conveyors; and based on the real-time material flow and the conveying requirement, the current operation mode of the workshop conveyor is selected, and operation parameters of the workshop conveyor in the current operation mode are adjusted. By setting the reasonable constraint rule and dividing different operation modes, the operation parameters of the workshop conveyor can be intelligently selected and adjusted according to the real-time material flow and the conveying requirement, it is ensured that the conveyor can operate in the optimal state under different working conditions, and the conveying efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of workshop conveyors, and in particular to an automatic adjustment method and system for workshop conveyors based on material conveying data. Background Art

[0002] In modern industrial production, material transportation is a key link that connects various production links and realizes the continuity of production processes. Traditional material transportation regulation technologies mostly rely on fixed speed and load settings, which are generally determined based on experience or static plans, and mainly rely on manual experience and simple control devices. These technologies usually adjust the operation of the conveyor based on preset rules and parameters. For example, according to the size of the material flow, the operator may manually adjust the speed or power of the conveyor, and often lack the ability to respond quickly to real-time production needs and the operating status of the conveyor; With the improvement of the level of industrial automation, some workshop conveyors have begun to integrate simple sensors and controllers to achieve basic regulation of conveying speed and load. However, most of these workshop conveyors use open-loop control, lacking comprehensive consideration and precise control of complex variables in the conveying process, such as fluctuations in material flow, optimization of conveying energy consumption, and synchronization with production rhythm.

[0003] There are some significant drawbacks in the existing workshop conveyor adjustment methods. First, these methods often rely on manual experience and intuition, lack of scientific and accurate data support. Due to the complexity and variability of the material conveying process, it is difficult to achieve accurate and real-time adjustment based on manual experience alone; secondly, the existing adjustment methods can often only consider limited parameters, such as material flow or conveying speed, while ignoring other important factors, such as conveying load, energy consumption and conveying rhythm. This one-sided consideration leads to unsatisfactory adjustment effects and the inability to achieve optimal conveying efficiency; in addition, the existing adjustment methods lack adaptive capabilities and cannot be adjusted according to real-time data and changing production needs, resulting in low conveying efficiency, high energy consumption and costs.

[0004] Due to the above-mentioned drawbacks of the existing technology, the efficiency and effect in the field of material transportation are often limited. The traditional workshop conveyor adjustment method relies on fixed control strategies and parameter settings, lacks flexibility and adaptability. This method cannot cope with the complex and changeable situations in the material transportation process, nor can it make full use of a large amount of material transportation data to achieve real-time and accurate adjustment, making it difficult for the workshop conveyor to operate in the optimal state, resulting in energy waste and low efficiency; therefore, a new workshop conveyor adjustment method is urgently needed. By combining multimodal deep learning technology with real-time data analysis, the intelligent adjustment of workshop conveyor operating parameters can be realized to improve the efficiency and quality of material transportation.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In response to the problems in the related technology, the present invention proposes an automatic adjustment method and system for a workshop conveyor based on material conveying data, which has the advantage of being able to intelligently select and adjust the operating parameters of the workshop conveyor according to the real-time material flow and conveying demand, thereby ensuring that the workshop conveyor can operate in the optimal state under different working conditions, thereby solving the problem in the prior art that it relies on fixed control strategies and parameter settings and cannot cope with the complex and changeable situations in the material conveying process.

[0007] To this end, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a method for automatic adjustment of a workshop conveyor based on material transportation data is provided, and the method for automatic adjustment of a workshop conveyor based on material transportation data comprises the following steps: S1. Based on the collected material transportation data, a multimodal data set is constructed, and the multimodal deep learning network is used to process the multimodal data set to obtain multidimensional transportation features; S2. Set constraint rules according to the operation parameters and historical data of the workshop conveyor, and divide the operation mode of the workshop conveyor; S3. Based on the real-time material flow and conveying demand, select the current operation mode of the workshop conveyor, and adjust the operation parameters of the workshop conveyor under the current operation mode; Setting constraint rules according to the operation parameters and historical data of the workshop conveyor and dividing the operation mode of the workshop conveyor includes the following steps: S21. Setting constraint rules for the automatic adjustment model of the workshop conveyor, including safety operation constraints, efficiency production demand constraints, cost control constraints and conveying rhythm constraints; S22, dividing the operation modes of the workshop conveyor into peak flow mode, valley flow mode and idle mode; S23. Based on the division results, design corresponding adjustment strategies for different operation modes.

[0008] Further, the material transport data includes material transport sequence data and material transport non-sequence data; Among them, the material transportation sequence data includes: transportation speed and transportation time; Material transportation non-sequential data include: transportation load, material flow and transportation energy consumption.

[0009] Furthermore, based on the collected material transportation data, a multimodal data set is constructed, and the multimodal deep learning network is used to process the multimodal data set to obtain multidimensional transportation features, including the following steps: S11. Integrate material transportation sequence data and material transportation non-sequence data to construct a multimodal data set; S12. Based on the multimodal deep learning network, the sequence data features of the multimodal data set are extracted using a single-dimensional convolutional layer, the non-sequence data features of the multimodal data set are extracted using a fully connected layer, and the sequence data features and non-sequence data features are fused using a long short-term memory layer. S13. Obtain the output vector of the last hidden layer and normalize it to obtain multi-dimensional transmission features.

[0010] Furthermore, setting the constraint rules of the automatic adjustment model of the workshop conveyor, including safety operation constraints, efficiency production demand constraints, cost control constraints and conveying rhythm constraints, includes the following steps: S211. Calculate and set the maximum safe load rate and build safe operation constraints based on the design specifications and historical operation data of the workshop conveyor; S212. Based on the efficiency curve and production demand of the workshop conveyor, set the minimum efficiency load rate and construct the efficiency production demand constraint; S213. Combining the energy consumption pattern and transportation cycle of the workshop conveyor, setting the cost control threshold and constructing the cost control constraint; S214. According to the transportation plan and work schedule of the workshop conveyor, the transportation rhythm is set and the transportation rhythm constraints are constructed.

[0011] Furthermore, dividing the operation modes of the workshop conveyor into peak flow mode, valley flow mode and idle mode includes the following steps: S221. Based on the statistical analysis of historical material flow data, define flow thresholds for peak flow mode, valley flow mode and idle mode; S222, setting a corresponding parameter range for each operation mode, including the speed, energy consumption power and load rate of the workshop conveyor; S223. Define the switching logic between different operation modes, including triggering conditions and switching procedures.

[0012] Furthermore, based on the division results, designing corresponding adjustment strategies for different operation modes includes the following steps: S231. Classify and define policy rule types according to the requirements of different operation modes; S232. Based on each policy rule type, specify associated operating parameters, including operating parameters of the workshop conveyor start-up, operation and stop stages; S233. According to the policy rule type and the associated operating parameters, set the logical conditions for parameter adjustment.

[0013] Further, based on the real-time material flow and conveying demand, selecting the current operation mode of the workshop conveyor and adjusting the operation parameters of the workshop conveyor in the current operation mode include the following steps: S31. Select the current operation mode of the workshop conveyor according to the real-time material flow and transportation demand; S32. Based on constraint rules and aiming at maximizing transportation efficiency, an automatic adjustment model of workshop conveyors in the current operation mode is constructed; S33. Based on the automatic adjustment model of the workshop conveyor, multi-dimensional conveying characteristics are input, and the operating parameters of the adjusted workshop conveyor are output.

[0014] Furthermore, based on the constraint rules and with the goal of maximizing transportation efficiency, the automatic adjustment model of the workshop conveyor in the current operation mode is constructed, which includes the following steps: S321, extracting the constraint rules of the automatic adjustment model of the workshop conveyor and constructing the expression of the constraint conditions; S322. According to the adjustment strategy of the current operation mode, the objective function is set to maximize the transportation efficiency, and an expression of the objective function is defined; S323. Based on the constraints and objective function, an automatic adjustment model of the workshop conveyor in the current operation mode is established.

[0015] Furthermore, the constraint condition is expressed as: ; ; ; ; In the formula, L Indicates the load rate of the workshop conveyor; L max Indicates the maximum safe load rate; L min Indicates the minimum efficiency load rate; p ( t ) represents the energy consumption of the workshop conveyor, C cost Indicates the cost control threshold; v Indicates the conveying speed of the workshop conveyor, v pro Indicates the conveying speed of the workshop conveyor under the conveying beat; The expression of the objective function is: ; In the formula, f ( x ) represents the objective function, which is used to maximize the transportation efficiency while taking into account the control cost; α and βRepresents the weight coefficient, which is used to balance the importance of transportation efficiency and cost control; Q material is the material flow rate, which indicates the amount of material transported per unit time; Eenergy is energy consumption, which indicates the energy consumed during the transportation process; Ccurrent The current cost indicates the cost consumption in the current operation mode.

[0016] According to another aspect of the present invention, there is also provided a workshop conveyor automatic adjustment system based on material transportation data, the workshop conveyor automatic adjustment system based on material transportation data comprising: The multi-dimensional transport feature module is used to construct a multi-modal data set based on the collected material transport data, and use the multi-modal deep learning network to process the multi-modal data set to obtain multi-dimensional transport features; The operation mode building module is used to set constraint rules according to the operation parameters and historical data of the workshop conveyor and divide the operation mode of the workshop conveyor; An operation parameter adjustment module is used to select the current operation mode of the workshop conveyor based on the real-time material flow and conveying demand, and adjust the operation parameters of the workshop conveyor under the current operation mode; Among them, the multi-dimensional transport feature module is connected with the operation parameter adjustment module through the operation mode construction module.

[0017] The beneficial effects of the present invention are: (1) By setting reasonable constraint rules and dividing different operating modes, the present invention can intelligently select and adjust the operating parameters of the workshop conveyor according to the real-time material flow and transportation demand. This flexible adjustment strategy can ensure that the conveyor can operate in the optimal state under different working conditions, improve the transportation efficiency, and reduce energy consumption and cost; at the same time, by utilizing the comprehensive collection and multi-modal processing of material transportation data, more accurate and comprehensive multi-dimensional transportation characteristics can be obtained, thereby providing a solid foundation for the automatic adjustment of the workshop conveyor. Not only the sequential data such as the transportation speed and time are considered, but also the non-sequential data such as the transportation load, material flow and energy consumption are comprehensively considered, so that the adjustment of the conveyor is more in line with the actual operating conditions; in addition, the present invention adopts deep learning networks and linear programming technology, which can automatically learn and optimize the adjustment strategy from a large amount of data. This method greatly reduces the need for manual intervention, reduces the possibility of human errors, and improves the reliability and stability of the workshop conveyor.

[0018] (2) The present invention can accurately adjust parameters such as the speed, power and load rate of the workshop conveyor to adapt to different production needs by real-time monitoring and analysis of material transportation data. This precise adjustment can ensure that the workshop conveyor operates efficiently in high-flow mode and saves energy in low-flow mode, thereby improving production efficiency and reducing energy consumption and operating costs. Secondly, by setting reasonable cost control constraints and minimum efficiency load rate, the present invention can ensure that the workshop conveyor minimizes energy consumption and operating costs while meeting production needs, thereby achieving refined cost control and helping to improve market competitiveness.

[0019] (3) By setting safe operation constraints and conveying rhythm constraints, the present invention can ensure that the workshop conveyor operates within a safe range and can adapt to the rhythm requirements of the production plan. This precise adjustment and control can effectively reduce the failure rate of the conveying system and improve the reliability and stability of the system. In addition, by real-time monitoring and analysis of material conveying data, the present invention can promptly detect and handle abnormal conditions in the conveying system, thereby reducing the occurrence of failures. This real-time monitoring and analysis not only helps to promptly discover potential problems, but also helps to quickly respond to and handle these problems, reducing the impact of failures on production. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 is a flow chart of a method for automatic adjustment of a workshop conveyor based on material transport data according to an embodiment of the present invention; Figure 2 It is a principle block diagram of a workshop conveyor automatic adjustment system based on material transportation data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0023] According to an embodiment of the present invention, a method and system for automatically adjusting a workshop conveyor based on material conveying data are provided.

[0024] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a method for automatic adjustment of a workshop conveyor based on material transportation data is provided, and the method for automatic adjustment of a workshop conveyor based on material transportation data comprises the following steps: S1. Based on the collected material transportation data, a multimodal data set is constructed, and the multimodal deep learning network is used to process the multimodal data set to obtain multidimensional transportation features; S2. Set constraint rules according to the operation parameters and historical data of the workshop conveyor, and divide the operation mode of the workshop conveyor; S3. Based on the real-time material flow and conveying demand, select the current operation mode of the workshop conveyor, and adjust the operation parameters of the workshop conveyor under the current operation mode; Setting constraint rules according to the operation parameters and historical data of the workshop conveyor and dividing the operation mode of the workshop conveyor includes the following steps: S21. Setting constraint rules for the automatic adjustment model of the workshop conveyor, including safety operation constraints, efficiency production demand constraints, cost control constraints and conveying rhythm constraints; S22, dividing the operation modes of the workshop conveyor into peak flow mode, valley flow mode and idle mode; S23. Based on the division results, design corresponding adjustment strategies for different operation modes.

[0025] In one embodiment, the material transport data includes material transport sequence data and material transport non-sequence data; Among them, the material transportation sequence data includes: transportation speed and transportation time; Material transportation non-sequential data include: transportation load, material flow and transportation energy consumption.

[0026] In one embodiment, constructing a multimodal data set based on the collected material transportation data, and processing the multimodal data set using a multimodal deep learning network to obtain multidimensional transportation features includes the following steps: S11. Integrate material transportation sequence data and material transportation non-sequence data to construct a multimodal data set; Specifically, the NoSQL database is used to import the real-time collected sequence data (conveyance speed, transportation time) and non-sequence data (conveyance load, material flow, transportation energy consumption) into a unified data table. The data is then arranged in chronological order through the timestamp field to ensure that the time point of each record is consistent. The moving average method is then used to fill in the missing data and establish a multimodal data set.

[0027] S12. Based on the multimodal deep learning network, the sequence data features of the multimodal data set are extracted using a single-dimensional convolutional layer, the non-sequence data features of the multimodal data set are extracted using a fully connected layer, and the sequence data features and non-sequence data features are fused using a long short-term memory layer. Specifically, a deep learning network with a convolutional layer and a recurrent layer is used. In this embodiment, a multimodal deep learning network with a CNN-LSTM architecture is used.

[0028] Specifically, CNN is used to extract sequence data features of sequence data. Here, the number and size of CNN filters can be adaptively adjusted according to the data. A 1D CNN model is designed, which contains learnable filters. These filters can automatically adjust according to the input sequence data to extract the most useful features; then for non-sequence data, the data is input into the Dense layer, and the fully connected layer is used to extract non-sequence data features; then the feature vectors of the two branches are concatenated in the time dimension and then input into the LSTM layer to simultaneously consider the dynamic changes of time series data and the static features of non-sequence data.

[0029] S13. Obtain the output vector of the last hidden layer and normalize it to obtain multi-dimensional transmission features.

[0030] Specifically, the output from the last hidden layer of the multimodal deep learning network is obtained as a multidimensional conveying feature vector, and then the feature vector is batch normalized and output in a standard form with zero mean and unit variance as the input of the subsequent workshop conveyor automatic adjustment model.

[0031] In one embodiment, setting the constraint rules of the automatic adjustment model of the workshop conveyor, including safety operation constraints, efficiency production demand constraints, cost control constraints and conveying rhythm constraints, includes the following steps: S211. Calculate and set the maximum safe load rate and build safe operation constraints based on the design specifications and historical operation data of the workshop conveyor; Specifically, the design specifications of the workshop conveyor are queried, and the historical operation data of the workshop conveyor in the past period of time (one year in this embodiment) is collected to find out the maximum stable operating load rate of the conveyor without any failure or safety problem. Considering the reliability and safety of long-term operation, a safety factor is usually set based on the maximum load capacity to reduce the operation risk, and then the maximum safe load rate is calculated and set. L max , the expression is: ; In the formula, L max Indicates the maximum safe load rate of the workshop conveyor; L h Indicates the maximum load rate allowed by the design specifications of the workshop conveyor; L d Indicates the maximum stable operating load rate shown in historical data; a q Indicates the safety factor.

[0032] In this embodiment, the maximum load rate allowed by the design specifications of the workshop conveyor is 98%, but the historical operation data shows that the workshop conveyor can operate stably without failure at the maximum stable operation load rate of 80%. For safety reasons, it is decided to use a safety factor of 90%, and the maximum safe load rate is finally calculated. L max =80%×0.9=72%, which is used as a safety operation constraint to ensure that the workshop conveyor operates within a safe range.

[0033] S212. Based on the efficiency curve and production demand of the workshop conveyor, set the minimum efficiency load rate and construct the efficiency production demand constraint; Specifically, by referring to the technical specifications provided by the manufacturer, collect the efficiency data of the workshop conveyor at different load rates, and then determine the daily or shift production goals, including the total amount of material required and the available working time. Plot the collected efficiency data into a graph with the load rate as the horizontal axis and the efficiency as the vertical axis. Then convert the production demand into load rate demand. For example, if the production demand is to transport 100 tons of material per day, and there are 8 hours of working time per day, then calculate the amount of material that needs to be transported per hour, and calculate the required average load rate based on the bandwidth of the conveyor and the density of the material.

[0034] In the above example, the efficiency curve of the workshop conveyor shows that when the load rate is 60%, the efficiency of the conveyor reaches a reasonable working point, which can meet the production needs without excessive energy consumption or excessive wear of the equipment; at the same time, through comparative analysis with the production plan, it is confirmed that at a load rate of 60%, the conveyor can complete the daily production target within the specified working time. Therefore, based on these data and analysis, the minimum efficiency load rate is set to 60%, that is, L min =0.6, thus obtaining the efficiency production demand constraint.

[0035] S213. Combining the energy consumption pattern and transportation cycle of the workshop conveyor, setting the cost control threshold and constructing the cost control constraint; Specifically, set a cost control threshold C cost, the threshold is the maximum allowable value of the energy consumption of the workshop conveyor per unit time, which is equal to the maximum kilowatt-hours of energy consumption of the workshop conveyor per hour. Then, a cost control constraint is constructed to ensure that the real-time energy consumption of the conveyor does not exceed the set energy consumption threshold at any given time. The expression of the cost control constraint is: ; ; In the formula, p ( t ) represents the energy consumption of the workshop conveyor; P Indicates the power of the workshop conveyor, in kW; v Indicates the running speed of the workshop conveyor, in m / min; L Indicates the load rate of the workshop conveyor.

[0036] S214. According to the transportation plan and work schedule of the workshop conveyor, the transportation rhythm is set and the transportation rhythm constraints are constructed.

[0037] Specifically, the transport plan and work schedule of the workshop conveyor usually have a predetermined cycle time, that is, the time required to produce a unit of product, and the conveying speed v The takt time of production plan must be consistent with T pro To ensure the continuity and efficiency of the production process, the expression of the conveying cycle constraint is: ; In the formula, v pro Indicates the conveying speed of the workshop conveyor under the conveying rhythm, the unit is m 2 / min; Q Indicates the amount of material that needs to be transported by the workshop conveyor, in m 3 ; T pro Indicates the takt time of the production plan, in min; W Indicates the material conveying bandwidth of the workshop conveyor, in m.

[0038] In one embodiment, dividing the operation mode of the workshop conveyor into a peak flow mode, a valley flow mode and an idle mode comprises the following steps: S221. Based on the statistical analysis of historical material flow data, define flow thresholds for peak flow mode, valley flow mode and idle mode; Specifically, based on the statistical analysis of historical material flow data, the flow threshold of the peak flow mode is defined as F peak , the flow threshold of the low flow mode is defined as F low , when the material flow is close to zero, it is defined as idle mode, and the flow threshold of idle mode is F idle .

[0039] S222, setting a corresponding parameter range for each operation mode, including the speed, energy consumption power and load rate of the workshop conveyor; Specifically, set the speed of the workshop conveyor for each operating mode V , Energy consumption P and load factor L In the above embodiment, for the peak flow mode, V peak =2m / min, P peak =5kW, L peak =0.8; for the low flow mode, V low =1m / min, P low =3kW, L low =0.6; for idle mode, V idle =0m / min, P idle =0.5kW, L idle =0.

[0040] S223. Define the switching logic between different operation modes, including triggering conditions and switching procedures.

[0041] Specifically, the switching logic between different operation modes is defined, including trigger conditions and switching processes. In the above embodiment, when the real-time material flow exceeds F peak and lasts for 5 minutes, the current mode is switched to the peak flow mode. F low If the material flow rate is not detected for 10 minutes, it will switch to the idle mode.

[0042] In one embodiment, based on the division results, designing corresponding adjustment strategies for different operation modes includes the following steps: S231. Classify and define policy rule types according to the requirements of different operation modes; Specifically, the strategy rule types are defined according to the requirements of different operating modes. Among them, the strategy rule types for the peak flow mode are: give priority to ensuring the conveying speed and load rate to cope with high flow demand; the strategy rule types for the valley flow mode are: optimize energy consumption, reduce speed and load rate, and reduce energy consumption; the strategy rule types for the idle mode are: maintain the lowest operating state and prepare to respond quickly to the upcoming material flow.

[0043] S232. Based on each policy rule type, specify associated operating parameters, including operating parameters of the workshop conveyor start-up, operation and stop stages; Specifically, based on each policy rule type, the associated operating parameters are specified, where for peak traffic mode, V = V peak , P = P peak , L = L peak ; For low flow mode, V = V low , P = P low , L = L low ; For idle mode, V = V idle , P = P idle , L = L idle .

[0044] S233. According to the policy rule type and the associated operating parameters, set the logical conditions for parameter adjustment.

[0045] Specifically, according to the policy rule type and the associated operating parameters, set the logical conditions for parameter adjustment. For example, if the current traffic is in peak mode and the real-time load rate is lower than L peak , then increase the power of the conveyor to increase the load rate; if it is currently in low flow mode and the energy consumption exceeds C cost , then reduce the conveyor speed to reduce energy consumption.

[0046] In one embodiment, based on the real-time material flow and conveying demand, selecting the current operating mode of the workshop conveyor and adjusting the operating parameters of the workshop conveyor in the current operating mode include the following steps: S31. Select the current operation mode of the workshop conveyor according to the real-time material flow and transportation demand; Specifically, if the real-time material flow is greater than or equal to the peak flow threshold F peak , the peak flow mode is selected; if the real-time material flow is less than the peak flow threshold and greater than or equal to the valley flow threshold F low , then select the valley flow mode; if the real-time material flow is less than the valley flow threshold F low , select idle mode.

[0047] S32. Based on constraint rules and aiming at maximizing transportation efficiency, an automatic adjustment model of workshop conveyors in the current operation mode is constructed; S33. Based on the automatic adjustment model of the workshop conveyor, multi-dimensional conveying characteristics are input, and the operating parameters of the adjusted workshop conveyor are output.

[0048] Specifically, the multi-dimensional conveying characteristics are input into the automatic adjustment model of the workshop conveyor, and the speed and load rate of the workshop conveyor are adjusted in real time according to the output adjusted operating parameters to match the production demand and meet the constraints.

[0049] In one embodiment, based on constraint rules and with the goal of maximizing transportation efficiency, constructing an automatic adjustment model for a workshop conveyor in the current operation mode includes the following steps: S321, extracting the constraint rules of the automatic adjustment model of the workshop conveyor and constructing the expression of the constraint conditions; S322. According to the adjustment strategy of the current operation mode, the objective function is set to maximize the transportation efficiency, and an expression of the objective function is defined; S323. Based on the constraints and objective function, an automatic adjustment model of the workshop conveyor in the current operation mode is established.

[0050] In one embodiment, the constraint condition is expressed as: ; ; ; ; In the formula, L Indicates the load rate of the workshop conveyor; L maxIndicates the maximum safe load rate; L min Indicates the minimum efficiency load rate; p ( t ) represents the energy consumption of the workshop conveyor, C cost Indicates the cost control threshold; v Indicates the conveying speed of the workshop conveyor, v pro Indicates the conveying speed of the workshop conveyor under the conveying beat; The expression of the objective function is: ; In the formula, f ( x ) represents the objective function, which is used to maximize the transportation efficiency while taking into account the control cost; α and β Represents the weight coefficient, which is used to balance the importance of transportation efficiency and cost control; Q material is the material flow rate, which indicates the amount of material transported per unit time; Eenergy is energy consumption, which indicates the energy consumed during the transportation process; Ccurrent The current cost indicates the cost consumption in the current operation mode. In this embodiment, it is calculated by multiplying the real-time energy consumption by the unit energy consumption cost.

[0051] like Figure 2 As shown, according to another embodiment of the present invention, there is also provided a workshop conveyor automatic adjustment system based on material transportation data, the workshop conveyor automatic adjustment system based on material transportation data comprises: The multi-dimensional transport feature module 1 is used to construct a multi-modal data set based on the collected material transport data, and use a multi-modal deep learning network to process the multi-modal data set to obtain multi-dimensional transport features; The operation mode construction module 2 is used to set constraint rules according to the operation parameters and historical data of the workshop conveyor and divide the operation mode of the workshop conveyor; The operation parameter adjustment module 3 is used to select the current operation mode of the workshop conveyor based on the real-time material flow and conveying demand, and adjust the operation parameters of the workshop conveyor under the current operation mode; Among them, the multi-dimensional transport characteristic module 1 is connected with the operation parameter adjustment module 3 through the operation mode construction module 2.

[0052] In summary, with the help of the above-mentioned technical scheme of the present invention, by setting reasonable constraint rules and dividing different operating modes, the operating parameters of the workshop conveyor can be intelligently selected and adjusted according to the real-time material flow and transportation demand. This flexible adjustment strategy can ensure that the conveyor can operate in the optimal state under different working conditions, improve the transportation efficiency, reduce energy consumption and cost, and utilize the comprehensive collection and multimodal processing of material transportation data to obtain more accurate and comprehensive multi-dimensional transportation characteristics, thereby providing a solid foundation for the automatic adjustment of the workshop conveyor. Not only the sequential data such as transportation speed and time are considered, but also the non-sequential data such as transportation load, material flow and energy consumption are comprehensively considered, so that the adjustment of the conveyor is more in line with the actual operating conditions. By adopting deep learning networks and linear programming technology, the present invention can automatically learn and optimize the adjustment strategy from a large amount of data. This method greatly reduces the need for manual intervention, reduces the possibility of human errors, and improves the reliability and stability of the workshop conveyor; at the same time, the present invention can accurately adjust the workshop conveyor by real-time monitoring and analysis of material transportation data. The speed, power and load rate of the machine can be adjusted to meet different production needs. This precise adjustment can ensure that the workshop conveyor runs efficiently in high-flow mode and saves energy in low-flow mode, thereby improving production efficiency and reducing energy consumption and operating costs. Secondly, by setting reasonable cost control constraints and minimum efficiency load rates, the present invention can ensure that the workshop conveyor can meet production needs while minimizing energy consumption and operating costs, achieving refined cost control, and helping to improve market competitiveness; in addition, by setting safe operation constraints and conveying rhythm constraints, the present invention can ensure that the workshop conveyor operates within a safe range and can adapt to the rhythm requirements of the production plan. This precise adjustment and control can effectively reduce the failure rate of the conveying system and improve the reliability and stability of the system. By real-time monitoring and analysis of material conveying data, the present invention can promptly detect and handle abnormal conditions in the conveying system, thereby reducing the occurrence of failures. This real-time monitoring and analysis not only helps to promptly discover potential problems, but also helps to quickly respond to and handle these problems, reducing the impact of failures on production.

[0053] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for automatic adjustment of a workshop conveyor based on material transportation data, characterized in that: The automatic adjustment method for a workshop conveyor based on material conveying data comprises the following steps: S1. Based on the collected material transportation data, a multimodal data set is constructed, and the multimodal deep learning network is used to process the multimodal data set to obtain multidimensional transportation features; S2. Set constraint rules according to the operation parameters and historical data of the workshop conveyor, and divide the operation mode of the workshop conveyor; S3. Based on the real-time material flow and conveying demand, select the current operation mode of the workshop conveyor, and adjust the operation parameters of the workshop conveyor under the current operation mode; The method of setting constraint rules according to the operating parameters and historical data of the workshop conveyor and dividing the operating mode of the workshop conveyor includes the following steps: S21. Setting constraint rules for the automatic adjustment model of the workshop conveyor, including safety operation constraints, efficiency production demand constraints, cost control constraints and conveying rhythm constraints; S22, dividing the operation modes of the workshop conveyor into peak flow mode, valley flow mode and idle mode; S23. Based on the division results, design corresponding adjustment strategies for different operation modes.

2. The method for automatic adjustment of a workshop conveyor based on material transportation data according to claim 1, characterized in that: The material transportation data includes material transportation sequence data and material transportation non-sequence data; Wherein, the material transport sequence data includes: transport speed and transport time; The material transportation non-sequential data includes: transportation load, material flow and transportation energy consumption.

3. The method for automatic adjustment of a workshop conveyor based on material transportation data according to claim 2 is characterized in that: The method of constructing a multimodal data set based on the collected material transportation data, and processing the multimodal data set using a multimodal deep learning network to obtain multidimensional transportation features includes the following steps: S11. Integrate material transportation sequence data and material transportation non-sequence data to construct a multimodal data set; S12. Based on the multimodal deep learning network, the sequence data features of the multimodal data set are extracted using a single-dimensional convolutional layer, the non-sequence data features of the multimodal data set are extracted using a fully connected layer, and the sequence data features and non-sequence data features are fused using a long short-term memory layer. S13. Obtain the output vector of the last hidden layer and normalize it to obtain multi-dimensional transmission features.

4. The method for automatic adjustment of a workshop conveyor based on material transportation data according to claim 3 is characterized in that: The constraint rules for setting the automatic adjustment model of the workshop conveyor, including safety operation constraints, efficiency production demand constraints, cost control constraints and conveying rhythm constraints, include the following steps: S211. Calculate and set the maximum safe load rate and build safe operation constraints based on the design specifications and historical operation data of the workshop conveyor; S212. Based on the efficiency curve and production demand of the workshop conveyor, set the minimum efficiency load rate and construct the efficiency production demand constraint; S213. Combining the energy consumption pattern and transportation cycle of the workshop conveyor, setting the cost control threshold and constructing the cost control constraint; S214. According to the transportation plan and work schedule of the workshop conveyor, the transportation rhythm is set and the transportation rhythm constraints are constructed.

5. The method for automatic adjustment of a workshop conveyor based on material transportation data according to claim 4 is characterized in that: The division of the operation modes of the workshop conveyor into peak flow mode, valley flow mode and idle mode comprises the following steps: S221. Based on the statistical analysis of historical material flow data, define flow thresholds for peak flow mode, valley flow mode and idle mode; S222, setting a corresponding parameter range for each operation mode, including the speed, energy consumption power and load rate of the workshop conveyor; S223. Define the switching logic between different operation modes, including triggering conditions and switching procedures.

6. The method for automatic adjustment of a workshop conveyor based on material transportation data according to claim 5, characterized in that: The design of corresponding adjustment strategies for different operation modes based on the division results includes the following steps: S231. Classify and define policy rule types according to the requirements of different operation modes; S232. Based on each policy rule type, specify associated operating parameters, including operating parameters of the workshop conveyor start-up, operation and stop stages; S233. According to the policy rule type and the associated operating parameters, set the logical conditions for parameter adjustment.

7. The method for automatic adjustment of a workshop conveyor based on material transportation data according to claim 6, characterized in that: The method of selecting the current operation mode of the workshop conveyor based on the real-time material flow and the conveying demand, and adjusting the operation parameters of the workshop conveyor under the current operation mode includes the following steps: S31. Select the current operation mode of the workshop conveyor according to the real-time material flow and transportation demand; S32. Based on constraint rules and aiming at maximizing transportation efficiency, an automatic adjustment model of workshop conveyors in the current operation mode is constructed; S33. Based on the automatic adjustment model of the workshop conveyor, multi-dimensional conveying characteristics are input, and the operating parameters of the adjusted workshop conveyor are output.

8. The method for automatic adjustment of a workshop conveyor based on material transportation data according to claim 7, characterized in that: The automatic adjustment model of the workshop conveyor in the current operation mode is constructed based on the constraint rules with the goal of maximizing the transportation efficiency, and includes the following steps: S321, extracting the constraint rules of the automatic adjustment model of the workshop conveyor and constructing the expression of the constraint conditions; S322. According to the adjustment strategy of the current operation mode, the objective function is set to maximize the transportation efficiency, and an expression of the objective function is defined; S323. Based on the constraints and objective function, an automatic adjustment model of the workshop conveyor in the current operation mode is established.

9. The method for automatic adjustment of a workshop conveyor based on material transportation data according to claim 8, characterized in that: The constraint condition is expressed as: ； ； ； ； In the formula, L Indicates the load rate of the workshop conveyor; L max Indicates the maximum safe load rate; L min Indicates the minimum efficiency load rate; p ( t ) represents the energy consumption of the workshop conveyor, C cost Indicates the cost control threshold; v Indicates the conveying speed of the workshop conveyor, v pro Indicates the conveying speed of the workshop conveyor under the conveying beat; The expression of the objective function is: ； In the formula, f ( x ) represents the objective function, which is used to maximize the transportation efficiency while taking into account the control cost; α and β Represents the weight coefficient, which is used to balance the importance of transportation efficiency and cost control; Q material is the material flow rate, which indicates the amount of material transported per unit time; Eenergy is energy consumption, which indicates the energy consumed during the transportation process; Ccurrent The current cost indicates the cost consumption in the current operation mode.

10. A workshop conveyor automatic adjustment system based on material transportation data, used to implement the workshop conveyor automatic adjustment method based on material transportation data according to any one of claims 1 to 9, characterized in that: The workshop conveyor automatic adjustment system based on material transportation data includes: The multi-dimensional transport feature module is used to construct a multi-modal data set based on the collected material transport data, and use the multi-modal deep learning network to process the multi-modal data set to obtain multi-dimensional transport features; The operation mode building module is used to set constraint rules according to the operation parameters and historical data of the workshop conveyor and divide the operation mode of the workshop conveyor; An operation parameter adjustment module is used to select the current operation mode of the workshop conveyor based on the real-time material flow and conveying demand, and adjust the operation parameters of the workshop conveyor under the current operation mode; Among them, the multi-dimensional transport feature module is connected to the operating parameter adjustment module through the operating mode construction module.

Images