A conveyor auxiliary control method and system

Abstract

The embodiments of this specification disclose a conveyor auxiliary control method and system, including: obtaining a first conveying parameter of the conveyor; determining a conveying coordination value of the conveyor based on the first conveying parameter; determining a second conveying parameter of the conveyor based on the conveying coordination value; wherein the second conveying parameter is an updated first conveying parameter; and adjusting parameters of the conveyor based on the second conveying parameter.

Description

Technical Field

[0001] The present invention relates to the field of conveyor control, and in particular to a conveyor auxiliary control method and system. Background Art

[0002] In a complete production process, multiple conveyors are usually deployed, each of which is responsible for transporting materials from different front-end links of the production line to subsequent processing or assembly stages. Currently, the general tendency is to adopt the industrial frequency constant speed operation mode. However, when the conveyor is in an empty or lightly loaded state, it may lead to waste of resources such as electricity. At the same time, constant speed operation may also cause the accumulation of materials during the conveying process, affecting the smoothness and efficiency of the production line.

[0003] CN112793989B provides an intelligent speed regulation method for a belt conveyor based on material monitoring. The material monitoring device collects the material load matrix in real time, predicts the optimal drive motor speed, and realizes precise frequency conversion speed regulation of the drive motor through the belt conveyor control system. However, it does not consider the need for coordinated control when the production line has multiple conveyors.

[0004] Therefore, it is necessary to provide a conveyor auxiliary control method that can adjust the speed of each conveyor to achieve control optimization. Summary of the invention

[0005] One or more embodiments of this specification provide a conveyor auxiliary control method. The method includes: obtaining a first conveying parameter of the conveyor; determining a conveying coordination value of the conveyor based on the first conveying parameter; determining a second conveying parameter of the conveyor based on the conveying coordination value; wherein the second conveying parameter is an updated first conveying parameter; and adjusting parameters of the conveyor based on the second conveying parameter.

[0006] One or more embodiments of the present specification provide a conveyor auxiliary control system, the system including a processor, including the processor configured to: obtain a first conveying parameter of the conveyor; determine a conveying coordination value of the conveyor based on the first conveying parameter; determine a second conveying parameter of the conveyor based on the conveying coordination value; wherein the second conveying parameter is an updated first conveying parameter; and adjust parameters of the conveyor based on the second conveying parameter. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0008] Figure 1is an exemplary flow chart of a conveyor auxiliary control method according to some embodiments of this specification;

[0009] Figure 2 is an exemplary schematic diagram of determining a delivery coordination value according to some embodiments of this specification;

[0010] Figure 3 is an exemplary schematic diagram of a first determination model according to some embodiments of this specification;

[0011] Figure 4 is an exemplary schematic diagram of determining a second delivery parameter according to some embodiments of this specification;

[0012] Figure 5 is an exemplary schematic diagram of a second determination model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0017] In the production process, the industrial frequency constant speed operation mode commonly used by the conveyor will lead to problems such as low efficiency of the production line and waste of resources. Therefore, different production requirements require dynamic adjustment of the operating speed of the conveyor. CN112793989B only considers the intelligent speed regulation when a conveyor transports materials, and does not consider how to regulate the speed and coordinate the control when multiple production lines are running together. Therefore, in some embodiments of the present description, the conveying coordination value of the conveyor is determined according to the first conveying parameter of the conveyor, and the second conveying parameter of the conveyor is determined according to the conveying coordination value, wherein the second conveying parameter is the updated first conveying parameter, and the conveyor is adjusted according to the second conveying parameter. Then, by adjusting the conveying parameters of the conveyor, the production line is made more coordinated and efficient.

[0018] Figure 1 is an exemplary flow chart of a conveyor auxiliary control method according to some embodiments of this specification. Figure 1 As shown, the process 100 includes the following steps. In some embodiments, the process 100 can be executed by a processor. In some embodiments, the processor can execute the process 100 according to a cycle, and the cycle can be directly preset by the processor.

[0019] Step 110, obtaining a first conveying parameter of the conveyor.

[0020] Conveyors are mechanical devices used to continuously transport materials, goods or products between different locations. For example, belt conveyors, chain conveyors, hanging conveyors, etc.

[0021] The first conveying parameter refers to various index parameters of the material being conveyed by the conveyor. For example, the first conveying parameter may include the type of material being conveyed, the speed at which the material is conveyed, and the like.

[0022] Material type is the classification of items that need to be transported. For example, material types can include solid materials, liquid materials, large materials, etc.

[0023] In some embodiments, the processor may call system preset data to obtain the first delivery parameter, wherein the first delivery parameter may be preset by the system.

[0024] Step 120: determining a conveying coordination value of the conveyor based on the first conveying parameter.

[0025] The conveying coordination value refers to a parameter used to measure the conveying state of the conveyor. The conveying state refers to the state of the conveyor, such as the speed of the conveyor.

[0026] The transport coordination value can be divided into different categories according to different transport states. In some embodiments, the transport coordination value can include three categories: too fast, too slow, and moderate. In some embodiments, the transport coordination value can also include more subdivided transport states such as super fast, fast, moderate, slow, and too slow.

[0027] In some embodiments, the processor may determine the transport coordination value in a variety of ways, such as by determining the transport coordination value of the conveyor based on the first transport parameter.

[0028] In some embodiments, the processor may determine the conveying coordination value of the conveyor by querying a preset table based on the first conveying parameter.

[0029] The preset table may include a correspondence between the first transport parameter and the transport coordination value in the historical data, wherein the preset table may be constructed based on a large number of historical first transport parameters and corresponding transport coordination values.

[0030] In some embodiments, the processor can count the speed distribution data of each material type in the historical data; determine the conveying coordination value corresponding to the speed interval where the speed distribution data of the lower n quantiles are located as slower, determine the conveying coordination value corresponding to the speed interval where the speed distribution data of the upper n quantiles are located as faster, and determine the conveying coordination value corresponding to the speed interval where the remaining speed distribution data outside the upper n quantiles and lower n quantiles are located as moderate, and include the conveying coordination value and its corresponding speed interval under each material type into a preset table.

[0031] In some embodiments, the value of n can be determined based on the discreteness of all speeds under each material type in the historical data. In some embodiments, the processor can determine a discreteness based on all speeds under a material type, and correspondingly determine a value of n. The discreteness is positively correlated with the value of n.

[0032] In some embodiments, the degree of discreteness can be calculated by counting the variance of the conveying speed of each material type, and taking the variance as the degree of discreteness of the data. For example, for solid materials, the degree of discreteness of the conveying speed is relatively small. Since the shape and size of solid materials are relatively fixed, the resistance and friction encountered during the conveying process are relatively stable. For example, for ore and stone, the change in conveying speed is not much different, so the degree of discreteness is small, and the value of n is also small.

[0033] In some embodiments, by analyzing the discrete degree of speed under material types in historical data, the value of n is determined, and considering the conveying conditions of different material types, the conveying efficiency can be effectively improved and the stability and safety of the conveying can be ensured.

[0034] In some embodiments, the conveying coordination value under the first conveying parameter is queried through a preset table, which fully considers the transmission conditions corresponding to different material types. By continuously adjusting the conveying parameters of the conveyor, the production line is made more coordinated, thereby achieving precise conveying control, ensuring that the operation of the conveyor is highly matched with actual needs, and improving production efficiency and quality.

[0035] Step 130: determining a second conveying parameter of the conveyor based on the conveying coordination value.

[0036] The second delivery parameter is the updated first delivery parameter.

[0037] In some embodiments, the processor adjusts the conveying parameters of the conveyor whose conveying coordination value is not moderate to the default conveying parameters, and the adjusted default conveying parameters of the conveyor are used as the second conveying parameters. The default conveying parameters can be preset by professionals in this field. In other embodiments, for the conveyor whose conveying coordination value is moderate, the processor retains the first conveying parameters and does not adjust the parameters, that is, the second conveying parameters are equal to the first conveying parameters.

[0038] In some embodiments, the processor may determine the second conveying parameter of the conveyor according to the load on the conveyor material and the material characteristics. For example, when the materials are densely distributed on the conveyor, the materials are heavy, or the materials are of high value, the conveying speed in the first conveying parameter may be appropriately reduced as the conveying speed in the second conveying parameter to ensure the safety of material transportation.

[0039] Step 140: Adjust the parameters of the conveyor based on the second conveying parameters.

[0040] In some embodiments, the processor may use the second conveying parameter as the current conveying parameter of the conveyor to adjust the parameter, that is, adjust the current first conveying parameter of the conveyor to the second conveying parameter.

[0041] In some embodiments, continuously adjusting the conveying parameters of the conveyor according to the conveying coordination value helps to enhance the adaptability of the conveyor to the conveyed materials, improve the coordination degree of the conveyor in conveying materials, and improve the conveying efficiency.

[0042] Figure 2 is an exemplary schematic diagram of determining a delivery coordination value according to some embodiments of the present specification.

[0043] In some embodiments, the processor may determine a transport coordination value 220 based on a first transport parameter 211 , a first load volume 212 of the conveyor, a second load volume 213 of the conveyor, and a third load volume 214 of the conveyor.

[0044] The first load 212 refers to the material accumulation amount of the material storage at the conveying starting point of the conveyor, wherein the material accumulation amount refers to the material mass.

[0045] The second load 213 refers to the material accumulation amount in the material storage at the conveying end point of the conveyor.

[0046] The third load 214 refers to the material load on the conveyor.

[0047] The first load 212, the second load 213, and the third load 214 can be determined based on a variety of methods. In some embodiments, the first load, the second load, and the third load can be determined based on a weighing device on the conveyor. The weighing device can be set at a material depot at the conveying start point of the conveyor, a material depot at the conveying end point, or any other location on the conveying range. The weighing device can include a weight sensor or other weighing devices.

[0048] In some embodiments, the third load 214 is determined based on a conveying image of at least one conveyor. In some embodiments, the processor scans the materials on the conveyor through image recognition technology to obtain the quantity of materials on the conveyor, and calculates the total load of the materials on the conveyor, i.e., the third load 214, by the quantity of materials on the conveyor and the unit material mass. For example, the total load of the materials on the conveyor is obtained by multiplying the quantity of materials by the unit material mass. The unit material mass can be determined by obtaining user input or calling system stored data.

[0049] In some embodiments, obtaining the third load quantity 214 through the conveying image can improve the efficiency of obtaining the material load quantity, avoid human errors, and provide a faster and more accurate third load quantity 214.

[0050] In some embodiments, the processor may determine the delivery coordination value 220 by a variety of methods based on the first delivery parameter 211 , the first load 212 , the second load 213 , and the third load 214 .

[0051] In some embodiments, the processor determines the conveying coordination value 220 of the conveyor through vector database matching based on the first conveying parameter 211, the first load 212, the second load 213, and the third load 214 of the conveyor. For example, for each conveyor, the processor can determine the conveying coordination value of the conveyor through vector matching based on the vector database.

[0052] In some embodiments, the processor may construct a feature vector corresponding to the conveyor based on the first conveying parameter, the first load amount, the second load amount, and the third load amount in the conveyor historical data.

[0053] The feature vector refers to a vector constructed based on the conveying characteristic information of each conveyor. There are many ways to construct a feature vector based on the conveying characteristic information of the conveyor. For example, a feature vector p is constructed based on the conveying characteristics (x, y, m, n) of the corresponding conveyor, where the conveying characteristics (x, y, m, n) can represent the corresponding first conveying parameter 211 as x, the first load 212 as y, the second load 213 as m, and the third load 214 as n.

[0054] In some embodiments, the processor can perform clustering based on the feature vector to form a preset number of cluster centers, use the feature vector corresponding to the cluster center as a reference vector, use the actual transport coordination value corresponding to the cluster center as a label of the reference vector, and record it in the vector database.

[0055] In some embodiments, the processor can further analyze and determine the actual transportation coordination value by counting the number of occurrences or durations of abnormal events in the historical transportation process: determine the transportation coordination value corresponding to the speed interval where the number of times or duration data of the lower n quantiles are located as slower, determine the transportation coordination value corresponding to the speed interval where the number of times or duration data of the upper n quantiles are located as faster, and determine the transportation coordination value corresponding to the speed interval where the remaining number of times or duration data located outside the range of the lower n quantiles and the upper n quantiles are located as moderate. For more information about n quantiles, see Figure 1 and its related description.

[0056] Among them, abnormal events may include conveyor empty, conveyor speed adjustment time interval less than a preset speed adjustment time threshold, excessive cargo accumulation on the conveyor and overflowing the conveyor conveying range, etc. In some embodiments, the processor may count abnormal events by obtaining user input, automatically counting by the system, or in any other feasible manner.

[0057] An empty conveyor can be manifested as the conveyor not transporting goods, but production is still going on.

[0058] The preset speed adjustment time threshold refers to the preset time reference value between two speed adjustments of the conveyor, which can be preset by the system. When the speed adjustment time interval of the conveyor is less than the preset speed adjustment time threshold, the speed adjustment frequency of the conveyor is too high.

[0059] In some embodiments, abnormal events may also include a situation where goods overflow at the front end of the conveyor and the rear end of the conveyor is empty. The front end of the conveyor refers to the conveying range from the midpoint of the conveying to the end point of the conveying; the rear end of the conveyor refers to the conveying range from the starting point of the conveying to the midpoint of the conveying.

[0060] In some embodiments, the processor may also determine the reference vector and its corresponding transport coordination value in other feasible ways.

[0061] In some embodiments, the processor can respectively calculate the distance between the reference vector and the vector to be matched, and determine the transport coordination value corresponding to the vector to be matched. The vector to be matched can be constructed based on the current first transport parameter, the first load, the second load, and the third load. The specific construction method is shown in the above feature vector. For example, a reference vector whose distance from the vector to be matched meets the preset conditions is used as the target vector, and the transport coordination value corresponding to the target vector is used as the transport coordination value corresponding to the vector to be matched. The preset conditions can be set according to the situation. For example, the preset conditions may be that the vector distance is minimum or the vector distance is less than a distance threshold, etc.

[0062] In some embodiments, by considering the material load at the starting point and the end point of the conveyor and the load on the conveyor, when measuring the transport status of the conveyor, it is more in line with the current transport situation of the conveyor, thereby obtaining a more accurate transport coordination value 220, thereby enhancing the reliability of the conveyor in transporting materials, avoiding material load accumulation or insufficient material load, and improving the efficiency of the entire transportation system.

[0063] Figure 3 is an exemplary schematic diagram of a first determination model according to some embodiments of the present specification.

[0064] In some embodiments, the processor may determine the delivery coordination value 340 for a future period of time based on the first determination model 320 based on the first delivery parameter 211 , the first load 212 , the second load 213 , and the third load 214 .

[0065] In some embodiments, the first determination model 320 may be a machine learning model, for example, a deep neural network model (DNN), a convolutional neural network model (CNN), or any combination thereof, or other custom model structures.

[0066] In some embodiments, the first determination model 320 can be obtained by training a first training sample with a label. The first training sample may include a sample first conveying parameter, a sample first load, a sample second load, and a sample third load of the sample conveyor at a first historical time. In some embodiments, the first training sample can be acquired based on historical data. The first label of the first training sample can be the actual conveying coordination value of the sample conveyor corresponding to the group of first training samples at the second historical time. The processor can obtain and / or manually annotate the first label based on historical data to determine the conveying coordination value of the conveyor at the second historical time. Wherein, the second historical time is later than the first historical time.

[0067] In some embodiments, the input of the first determination model 320 also includes material characteristics 310 of at least one conveyor.

[0068] Material characteristics 310 refer to various properties and features of a material, such as material shape, material composition, material size, etc. The material characteristics may be determined by obtaining user input, calling system preset data, or other feasible methods.

[0069] In some embodiments, the input of the first determination model 320 takes into account the material characteristics 310 , thereby improving the accuracy of the first determination model 320 in determining the transportation coordination value 340 for a period of time in the future, and being more in line with the actual transportation environment.

[0070] In some embodiments, the first determination model 320 includes a feature extraction layer 321 and a coordination value measurement layer 322, and the feature extraction layer 321 and the coordination value measurement layer 322 can be machine learning models. For example, the feature extraction layer 321 can be a long short-term memory network (Long Short-Term Memory, LSTM), and the coordination value measurement layer 322 can be a CNN.

[0071] The feature extraction layer 321 is used to determine the load distribution feature 330 based on the first load 212 , the second load 213 , the third load 214 , and the material feature 310 . The coordination value measurement layer 322 is used to determine the transport coordination value 340 for a future period of time based on the load distribution feature 330 and the first transport parameter 211 .

[0072] Load distribution characteristics refer to the characteristics that represent the material load distribution, such as the location of material distribution, the uniformity of material distribution, etc.

[0073] In some embodiments, the output of the feature extraction layer 321 may be the input of the coordination value measurement layer 322 , and the coordination value measurement layer 322 and the feature extraction layer 321 may be jointly trained.

[0074] In some embodiments, the sample data of the joint training includes the sample first load, sample second load, sample third load, and sample material characteristics of the sample conveyor at the first historical time, and the first label is the actual conveying coordination value of the sample conveyor at the second historical time. For more information about the sample data of the joint training and the first label, please refer to the related description of the first training sample and the first label of the first determination model 320.

[0075] During training, the processor inputs the sample first load, sample second load, sample third load, and sample material features into the feature extraction layer 321 to obtain the output of the feature extraction layer 321; the output of the feature extraction layer 321 and the sample first conveying parameter are input into the coordination value measurement layer 322 to obtain the output of the coordination value measurement layer 322. A loss function is constructed based on the output of the coordination value measurement layer 322 and the second label, and the parameters of the coordination value measurement layer 322 and the feature extraction layer 321 are synchronously updated. Through parameter updating, the trained coordination value measurement layer 322 and feature extraction layer 321 are obtained.

[0076] The first determination model 320 can be trained on other servers or computers with higher computing power, and then installed on the processor after completion.

[0077] In some embodiments, the material features 310 are fully considered through the training of the feature extraction layer 321 and the coordination value measurement layer 322, so that the transportation characteristics of different materials can be taken into account when the conveyor transports the materials.

[0078] In some embodiments, based on relevant data reflecting the conveying conditions, the conveying coordination value for a period of time in the future is predicted, taking into account the influence of the material load and the characteristics of different materials during conveying by the conveyor, which further conforms to the actual situation, enhances the adaptability of the conveyor to the conveyed materials, and is more conducive to further improving the accuracy of the first determination model 320 in determining the conveying coordination value for a period of time in the future.

[0079] Figure 4 is an exemplary schematic diagram of determining the second delivery parameter according to some embodiments of the present specification.

[0080] In some embodiments, the processor may determine the second transport parameter 420 based on the target production parameter 410, the transport coordination value 220, and the first transport parameter 211. For details on the transport coordination value, the first transport parameter, and the second transport parameter, see Figure 1 Corresponding description.

[0081] The target production parameters 410 refer to a combination of production parameters such as performance indicators and production ratios corresponding to the products produced by the production line. For example, the target production parameters 410 may include the target output speed of the product produced and the material ratio required to produce the product.

[0082] In some embodiments, the processor can determine the second conveying parameter in a variety of ways. For example, the processor can determine the second conveying parameter by querying the second conveying parameter reference table based on the target production parameter, the conveying coordination value, and the first conveying parameter. Among them, the second conveying parameter reference table includes reference target production parameters, reference conveying coordination values, and reference first conveying parameters, and the second conveying parameters corresponding to the aforementioned reference target production parameters, reference conveying coordination values, and reference first conveying parameters. The processor can select relevant data (for example, target production parameters, conveying coordination values, first conveying parameters, and second conveying parameters) in which the production parameters meet production expectations and the conveying coordination values ​​are moderate based on the historical operation data of the conveyor auxiliary control system and include them in the second conveying parameter reference table.

[0083] In some embodiments, the processor may determine the second delivery parameter by sequentially executing the following steps S1-S4.

[0084] S1. First screening: first screen out the production parameters, transportation coordination values, first transportation parameters and other data of the production products with the same product types in the historical data as the first rough selection data, and enter them into the first rough selection database.

[0085] S2, second screening: quantify the production parameters of the first rough selection data in the first rough selection database into digital vectors Ai, and quantify the target production parameters into digital vectors B; calculate the similarity between digital vectors B and each digital vector Ai, and determine the first rough selection data with a similarity greater than a similarity threshold as the second rough selection data, and include it in the second rough selection database. The quantization method includes, for example, coding, conversion formula, etc.

[0086] In some embodiments, the similarity threshold of the first coarsely selected data is related to the complexity of the produced product. The similarity threshold is negatively correlated with the complexity of the produced product.

[0087] In some embodiments, the processor may determine the similarity threshold based on the complexity of the production product. For example, when the complexity of the production product increases, the similarity threshold decreases accordingly. As an example only, the processor may determine the complexity of the production product based on the number of raw material types involved in the production of all products and the number of types of all products through formula (1).

[0088] Production complexity = k1*the average number of raw materials involved in the production of all products + k2*the number of all product types (1)

[0089] Among them, k1 and k2 are preset order of magnitude parameters.

[0090] In some embodiments of the present specification, the processor can dynamically determine the similarity threshold based on the complexity of the product being produced, and the system can more flexibly adapt to production environments of different complexities. For example, when the complexity of the product being produced is high, the system can automatically reduce the similarity threshold, and vice versa, thereby improving the adaptability and accuracy of the system.

[0091] S3. Third screening: Based on the second rough selection database, the data delivered in the subsequent period of time is screened for the third time, and the data whose delivery coordination value does not meet the quality requirements (for example, the delivery coordination value is not moderate) is eliminated, and the second rough selection data left after the screening is used as sample data (including sample production parameters, sample delivery coordination value, sample first delivery parameter), and is included in the sample database. Among them, the length of the subsequent period of time needs to be preset in advance. For example, the length of time can be a cycle, and more cycle-related content can be found in Figure 1 And related instructions.

[0092] S4. Determine the second transport parameter: construct a first vector with the current transport coordination value 220 and the first transport parameter 211. Similarly, construct the sample data in the sample database as a second vector, calculate the vector similarity between the first vector and the second vector, and use the transport parameter of the sample data corresponding to the second vector with the highest similarity in a subsequent period of time as the second transport parameter. The similarity measurement method may be cosine similarity, Euclidean distance, etc.

[0093] It is understandable that the processor can execute one or more steps of the first screening, the second screening and the third screening, and the execution order can be adjusted according to actual production needs. In some embodiments, the first rough selection data can also be used as sample data and counted into the vector database.

[0094] In some embodiments of the present specification, the processor vectorizes the current transport coordination value and the first transport parameter, and compares the similarity with the first rough selected data, and selects the future transport parameters of the most similar case as a reference. This method integrates historical successful experience and real-time production conditions, provides a scientific basis for production optimization, reduces trial and error costs, and improves efficiency and quality.

[0095] In some embodiments of the present specification, the processor can achieve accurate determination and optimal setting of the second conveying parameter of the conveyor based on comprehensive consideration of multiple factors such as conveying coordination value, target production parameters, historical data and complexity of production products, thereby showing significant beneficial effects in terms of accuracy of production decisions, system adaptability and flexibility, and improved product quality.

[0096] Figure 5 is an exemplary schematic diagram of a second determination model according to some embodiments of the present specification.

[0097] In some embodiments, the processor can construct a transmission map based on the target production parameters, the delivery coordination value, and the first delivery parameter; based on the transmission map, determine the second delivery parameter through a second determination model; wherein the second determination model is a machine learning model.

[0098] The transmission map 510 is a multi-dimensional relationship diagram constructed based on the target production parameter, the transmission coordination value and the first transmission parameter. The transmission map reflects how these parameters affect each other and determine the second transmission parameter.

[0099] The transmission graph 510 may include a plurality of nodes 510 - 1 and a plurality of edges 510 - 2 .

[0100] In some embodiments, nodes of the transmission graph include transit points and / or processing points.

[0101] The transfer point refers to the starting point or the end point of the material transport on the conveyor, that is, the first end corresponding to the first load of the conveyor and the second end corresponding to the second load. The transfer point is mainly for the flow of materials, and no processing is performed.

[0102] A processing site is a location where material assembly and production takes place. For example, a processing site can perform operations that transform input materials into finished products.

[0103] The attributes of the transfer point include the material load of the node. The material load reflects the amount of material on the current node. In some embodiments, the processor can determine the material load by obtaining weight data recorded by a weighing device on the conveyor. For more information about the weighing device, see Figure 2 Corresponding description.

[0104] The properties of the processing point mainly include the target production parameters of the node. In some embodiments, the processor can obtain the target production parameters by obtaining user input, calling system preset data, etc. Among them, more information about the target production parameters can be found in Figure 4 And related instructions.

[0105] In some embodiments, there is a conveyor transport relationship between the nodes, and the processor connects the two nodes to form an edge based on the conveyor transport relationship. The edge attributes of each edge include a first transport parameter and a transport coordination value. For more information about the first transport parameter and the transport coordination value, see Figure 1 And related instructions.

[0106] In some embodiments of the present disclosure, the processor can accurately grasp the real-time status and requirements of each link in the production process by clarifying the nodes and their attributes in the transmission map, which helps to optimize resource allocation, reduce waiting time and material backlog, and thus improve overall production efficiency.

[0107] In some embodiments, the node attributes of the nodes (including transfer points and / or processing points) of the transmission map also include material characteristics of the transmitted materials. Among them, the material characteristics include the shape of the material and the mass of a single material. In some embodiments, the processor can obtain the material characteristics by obtaining user input, calling system preset data, etc.

[0108] In some embodiments, the edge attributes of the edge of the transmission graph also include a transmission coordination value for a period of time in the future. For more information on the transmission coordination value for a period of time in the future, please refer to Figure 3 Corresponding description.

[0109] In some embodiments of this specification, the node attributes include material characteristics of the transported materials, such as material shape and individual material mass, which enables the system to handle different types of materials more accurately. Understanding the basic properties of materials helps optimize storage, handling and processing, and reduces losses and delays caused by mismatched or improperly handled materials.

[0110] The second determination model 520 refers to a model for determining the second transmission parameter 420. In some embodiments, the second determination model 520 may be a machine learning model. For example, the second determination model 520 may be a graph neural network model (GNN). The input of the second determination model 520 may be a transmission graph, and the output may be the second transmission parameter 420 corresponding to each edge in the transmission graph.

[0111] In some embodiments, the second determination model can be obtained by training multiple second training samples with second labels. For example, multiple second training samples with second labels can be input into the initial second determination model, and a loss function can be constructed by the second labels and the results of the initial second determination model, and the parameters of the initial second determination model can be iteratively updated based on the loss function. When the loss function of the initial second determination model meets the preset conditions, the model training is completed and the trained second determination model is obtained. Among them, the preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0112] In some embodiments, the second training sample of the second determination model 520 may be a sample transmission map. The sample transmission map may be constructed based on historical production parameters, historical transmission coordination values, and historical first transmission parameters of the sample conveyor at a third historical time.

[0113] In some embodiments, the second label of the second training sample is the actual conveying parameter of the sample conveyor corresponding to the second training sample at a fourth historical time, wherein the fourth historical time is a period of time subsequent to the third historical time.

[0114] The second training sample can also come from Figure 4 The sample data obtained in step S4 in step S4. For example, the sample transmission spectrum can be based on Figure 4 The sample production parameters, sample delivery coordination values, and sample first delivery parameters in the sample data obtained are constructed. For more information about the sample data, please refer to the relevant instructions in the corresponding part.

[0115] In some embodiments of the present specification, the processor can ensure smooth transportation during the production process based on the constructed transmission map and the actual topological connection relationship between the conveyors in the production process, and improve the accuracy of the second determined parameter, so as to be closer to the actual production situation.

[0116] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0117] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0118] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0119] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0120] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0121] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0122] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A conveyor auxiliary control method, characterized in that: The method is executed by a processor, comprising: Acquire a first conveying parameter of the conveyor, wherein the first conveying parameter is various index parameters of the material being conveyed by the conveyor, including: material type and material conveying speed; Determining a conveying coordination value of the conveyor based on the first conveying parameter includes: Based on the first conveying parameter, the first load, the second load, the third load and the material characteristics, the conveying coordination value for a future period of time is determined through a first determination model; wherein the first load is the material accumulation amount in the material warehouse at the conveying starting point of the conveyor, the second load is the material accumulation amount in the material warehouse at the conveying end point of the conveyor, the third load is the material load on the conveyor, the material characteristics are various properties and characteristics of the materials, and the first determination model is a machine learning model, including a feature extraction layer and a coordination value measurement layer; the feature extraction layer determines the load distribution characteristics based on the first load, the second load, the third load and the material characteristics; the coordination value measurement layer determines the conveying coordination value for a future period of time based on the load distribution characteristics and the first conveying parameter; the feature extraction layer and the coordination value measurement layer are obtained through joint training; the conveying coordination value is a parameter for measuring the conveying state of the conveyor; or Based on the first conveying parameter, the conveying coordination value of the conveyor is determined by querying a preset table; wherein the preset table includes the correspondence between the first conveying parameter and the conveying coordination value in the historical data; the preset table is constructed based on a large number of historical first conveying parameters and the corresponding conveying coordination values, including: counting the speed distribution data under each material type in the historical data; determining the conveying coordination value corresponding to the speed interval where the speed distribution data of the lower n quantiles are located as slower, determining the conveying coordination value corresponding to the speed interval where the speed distribution data of the upper n quantiles are located as faster, and determining the conveying coordination value corresponding to the speed interval where the remaining speed distribution data outside the upper n quantiles and lower n quantiles are located as moderate, and counting the conveying coordination value under each material type and its corresponding speed interval into the preset table; wherein the value of n is determined according to the discrete degree of all speeds under each material type in the historical data; Determining a second conveying parameter of the conveyor based on the conveying coordination value includes: determining the second conveying parameter based on a target production parameter, the conveying coordination value, and the first conveying parameter; wherein the second conveying parameter is the updated first conveying parameter; Based on the second conveying parameter, parameters of the conveyor are adjusted.

2. The method according to claim 1, characterized in that The determining the second transport parameter based on the target production parameter, the transport coordination value, and the first transport parameter comprises: Constructing a transmission map based on the target production parameter, the transmission coordination value, and the first transmission parameter; Based on the transmission spectrum, the second delivery parameter is determined by a second determination model; wherein the second determination model is a machine learning model.

3. A conveyor auxiliary control system, characterized in that: The system includes a processor configured to: Acquire a first conveying parameter of the conveyor, wherein the first conveying parameter is various index parameters of the material being conveyed by the conveyor, including: material type and material conveying speed; Determining a conveying coordination value of the conveyor based on the first conveying parameter includes: Based on the first conveying parameter, the first load, the second load, the third load and the material characteristics, the conveying coordination value for a future period of time is determined through a first determination model; wherein the first load is the material accumulation amount in the material warehouse at the conveying starting point of the conveyor, the second load is the material accumulation amount in the material warehouse at the conveying end point of the conveyor, the third load is the material load on the conveyor, the material characteristics are various properties and characteristics of the materials, and the first determination model is a machine learning model, including a feature extraction layer and a coordination value measurement layer; the feature extraction layer determines the load distribution characteristics based on the first load, the second load, the third load and the material characteristics; the coordination value measurement layer determines the conveying coordination value for a future period of time based on the load distribution characteristics and the first conveying parameter; the feature extraction layer and the coordination value measurement layer are obtained through joint training; the conveying coordination value is a parameter for measuring the conveying state of the conveyor; or Based on the first conveying parameter, the conveying coordination value of the conveyor is determined by querying a preset table; wherein the preset table includes the correspondence between the first conveying parameter and the conveying coordination value in the historical data; the preset table is constructed based on a large number of historical first conveying parameters and the corresponding conveying coordination values, including: counting the speed distribution data under each material type in the historical data; determining the conveying coordination value corresponding to the speed interval where the speed distribution data of the lower n quantiles are located as slower, determining the conveying coordination value corresponding to the speed interval where the speed distribution data of the upper n quantiles are located as faster, and determining the conveying coordination value corresponding to the speed interval where the remaining speed distribution data outside the upper n quantiles and lower n quantiles are located as moderate, and counting the conveying coordination value under each material type and its corresponding speed interval into the preset table; wherein the value of n is determined according to the discrete degree of all speeds under each material type in the historical data; Determining a second conveying parameter of the conveyor based on the conveying coordination value includes: determining the second conveying parameter based on a target production parameter, the conveying coordination value, and the first conveying parameter; wherein the second conveying parameter is the updated first conveying parameter; Based on the second conveying parameter, parameters of the conveyor are adjusted.

4. The system according to claim 3, characterized in that The processor is further configured to: Constructing a transmission map based on the target production parameter, the transmission coordination value, and the first transmission parameter; Based on the transmission spectrum, the second delivery parameter is determined by a second determination model; wherein the second determination model is a machine learning model.

Images