Method and apparatus for determining the operation trajectory curve, and electronic equipment.

Abstract

The present application discloses a method and apparatus for determining an operation trajectory curve and an electronic device, the method includes the steps of: obtaining operation data and production data of multiple batches of a production facility; performing a combining operation on the operation data and production data corresponding to the same collection date in the multiple batches to obtain a combined data set; determining a similarity between the combined data in the combined data set, classifying the combined data in the combined data set according to the similarity, and obtaining multiple classes of data; selecting target-type data from the multiple classes of data, determining weight values ​​corresponding to operation parameters of different batches in the target-type data, and determining an operation trajectory curve corresponding to the target-type data according to at least the weight values ​​and the values ​​of the operation parameters in the batches corresponding to the weight values.

Description

Cross-reference of related applications

[0001] This application claims priority to a Chinese patent application filed with the China National Patent Office on September 19, 2022, with priority number 202211137659.2, titled "Method and apparatus for determining an operation trajectory curve and electronic device," the entirety of which is incorporated into this application by reference. [Technical Field]

[0002] This application relates to the field of production design in process industries, and more specifically to a method and apparatus for determining operation trajectory curves, as well as electronic equipment. [Background technology]

[0003] In intermittent production in process industries, a standard curve of the operation trajectory is generally created before production for each batch, and the underlying control system operates according to this standard curve. However, in actual processes, the initial state of the production equipment is not perfectly identical across different batches. In such cases, operators adjust the operation trajectory during production based on their experience, resulting in variations in the yield and quality of the final product for each batch. Such adjustments are somewhat subjective, primarily qualitative, and lack quantifiable characteristics, making precise adjustment difficult. Therefore, it is necessary to obtain an optimal standard curve of the operation trajectory by analyzing the production results and operation trajectories of multiple batches.

[0004] In related technologies, the generation of standard curves for operation trajectories is generally done manually, making it inadequate to adapt to gradual changes in production equipment or evolving production needs. No effective solution to this problem has yet been proposed. [Overview of the project] [Problems that the invention aims to solve]

[0005] The embodiments of this application provide a method and apparatus for determining an operation trajectory curve, as well as electronic equipment, in order to at least solve the problem that the generation of standard curves for operation trajectories in the conventional method is generally done manually and cannot be adapted to gradual changes in production equipment or changes in production needs. [Means for solving the problem]

[0006] According to one aspect of an embodiment of the present invention, a method for determining an operation trajectory curve is provided, comprising the steps of: acquiring operational data and output data in multiple batches of production equipment, wherein the operational data is data collected by different meters, and the output data is product data relating to products produced in the production equipment, and each of the multiple batches corresponds to a different collection date; performing a join operation on the operational data and output data corresponding to the same collection date in the multiple batches to obtain a joined dataset; determining the similarity between the joined data in the joined dataset, classifying the joined data in the joined dataset according to the similarity, and obtaining multiple classes of data by classifying data whose similarity is greater than a preset threshold into one class; selecting target type data from the multiple classes of data, and determining weight values ​​corresponding to different batch operation parameters in the target type data, wherein the target type data is data from any of the multiple classes of data, and the operation parameter is at least one controllable data from the operational data; and determining an operation trajectory curve corresponding to the target type data according to at least the weight values ​​and the values ​​of the operation parameters in the batches corresponding to the weight values.

[0007] In some embodiments of the present invention, the step of performing a join operation on operational data and production data corresponding to the same collection date in multiple batches includes the steps of obtaining operational time corresponding to operational data; aligning operational data having the same operational time, sorting them according to operational time to obtain first data; joining the first data with production data corresponding to the same collection date to obtain joined data; and determining joined data corresponding to different collection dates to obtain a joined dataset.

[0008] In some embodiments of the present invention, the step of determining weight values ​​corresponding to different batch operation parameters in data of a target type includes the steps of obtaining collection dates corresponding to different batch operation parameters in data of a target type to obtain a set of collection dates, sorting the set of collection dates in descending order from the current date to obtain a target collection date set, and determining weight values ​​for batches corresponding to the set of collection dates in the target collection date set.

[0009] In some embodiments of the present invention, the step of determining batch weights corresponding to multiple collection dates in a target collection date set includes the step of determining a weight between batches corresponding to two adjacent dates in the target collection date set, wherein the weight of the batch corresponding to the first of the two adjacent dates is a predetermined multiple of the weight of the batch corresponding to the second date, the first date is the one of the two adjacent dates closer to the current date, the second date is the one of the two adjacent dates further from the current date, and the predetermined multiple is any value greater than 1.

[0010] In some embodiments of the present invention, after determining the weight values ​​between batches corresponding to two adjacent dates in a target collection date set, the method further includes the steps of: obtaining a weight set of batches corresponding to all dates in the target collection date set; constructing an equation according to the numerical relationships between all weight values ​​in the weight set; and solving the equation to obtain a first weight value between batches corresponding to two adjacent dates in the target collection date set.

[0011] In some embodiments of the present invention, the step of determining an operation trajectory curve corresponding to target type data includes the steps of determining a target weight value for a batch corresponding to each date in a target collection date set according to a first weight value, and determining a target operation parameter according to the target weight value and the value of the operation parameter at different operating times of the batch corresponding to the target weight value, wherein the target operation parameter is the value of the operation parameter at different operating times of the operation trajectory curve corresponding to target type data.

[0012] In some embodiments of the present invention, the operation trajectory curve is a curve in a coordinate system established with the operating time as the horizontal coordinate and the values ​​of the operation parameters during the operating time as the vertical coordinate.

[0013] According to another aspect of the present invention, an acquisition module configured to acquire operational data and output data in multiple batches of production equipment, wherein the operational data is data collected by different meters, and the output data is product data relating to products produced in the production equipment, and each of the multiple batches corresponds to a different collection date; a joining module configured to perform a join operation on the operational data and output data corresponding to the same collection date in the multiple batches to obtain a joined dataset; and a class that determines the similarity between the joined data in the joined dataset, classifies the joined data in the joined dataset according to the similarity, and classifies the data whose similarity is greater than a preset threshold into one class. A device for determining an operation trajectory curve is further provided, comprising: a classification module configured to obtain data of a batch; a first decision module configured to select data of a target type from a plurality of classes of data and to determine weight values ​​corresponding to different batches of operation parameters in the data of the target type, wherein the data of the target type is data of any of the plurality of classes of data, and the operation parameters are at least one controllable data from the operation data; and a second decision module configured to determine an operation trajectory curve corresponding to the data of the target type according to at least weight values ​​and the values ​​of the operation parameters in the batch corresponding to the weight values.

[0014] Further, according to yet another aspect of the embodiment of the present invention, electronic equipment is provided, comprising: a memory configured to store program instructions; and a processor connected to the memory, wherein the processor acquires operational data and output data in multiple batches of production equipment, the operational data being data collected by different meters; the output data being product data relating to products produced in the production equipment, each of the multiple batches corresponding to a different collection date; performs a join operation on the operational data and output data corresponding to the same collection date in the multiple batches to obtain a join dataset; determines the similarity between the join data in the join dataset; classifies the join data in the join dataset according to the similarity to obtain multiple classes of data, classifying data whose similarity is greater than a preset threshold into one class; selects target type data from the multiple classes of data; determines weight values ​​corresponding to different batch operation parameters in the target type data, the target type data being data in any of the multiple classes of data; and the operation parameters being at least one controllable data from the operational data; and determines an operation trajectory curve corresponding to the target type data according to at least the weight values ​​and the values ​​of the operation parameters in the batches corresponding to the weight values.

[0015] Further, according to yet another aspect of the embodiments of the present application, a non-volatile storage medium containing a stored computer program is provided, wherein a device on which the non-volatile storage medium is located executes the method for determining the operation trajectory curve described above by executing the computer program. [Effects of the Invention]

[0016] In the embodiments of the present application, operation data and output data in a plurality of batches of production equipment are acquired, a joining operation is performed on the operation data and output data corresponding to the same collection date in the plurality of batches to obtain a joined dataset, and the similarity between the joined data in the joined dataset is determined. The joined data in the joined dataset is classified according to the similarity to obtain data of a plurality of classes. Then, data of a target type is selected from the data of the plurality of classes, a weight value corresponding to the operation parameters of different batches in the data of the target type is determined, and at least according to the weight value and the value of the operation parameters in the batch corresponding to the weight value, an operation trajectory curve corresponding to the data of the target type is determined, thereby achieving the purpose of automatically generating an operation trajectory during production, realizing the technical effect of improving the generation efficiency of the operation trajectory, and further solving the problem that the generation of the standard curve of the conventional operation trajectory is generally performed manually and cannot adapt to the gradual changes of production equipment and the changes of production needs.

Brief Description of the Drawings

[0017] The drawings described herein are for further understanding of the present application, constitute a part of the present application, and the schematic embodiments and their descriptions in the present application are for explaining the present application and do not unduly limit the present application. In the drawings, [Figure 1] It is a hardware configuration block diagram of a computer terminal (or electronic device) for realizing the method for determining an operation trajectory curve according to an embodiment of the present application. [Figure 2] It is a flowchart of the method for determining an operation trajectory curve according to an embodiment of the present application. [Figure 3] It is a configuration diagram of a device for determining an operation trajectory curve according to an embodiment of the present application.

Modes for Carrying Out the Invention

[0018] Hereinafter, in order for those skilled in the art to better understand the aspects of the present application, while referring to the drawings of the embodiments of the present application, the technical aspects of the embodiments of the present application will be clearly and completely described. It is needless to say that the described embodiments are only some of the embodiments of the present application, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative labor should also be included within the protection scope of the present application.

[0019] In addition, terms such as "first", "second", etc. in the description, claims and the above-mentioned drawings of the present application are for distinguishing similar objects and not for explaining a specific order or priority. It should be understood that the numbers used in this way can be interchanged as appropriate in order to make the embodiments of the present application described herein be implemented in an order other than the order shown or described herein. Also, the terms "comprising", "having" and any variations thereof are intended to cover what is included without being exclusive. For example, a process, method, system, product or device including a series of steps or units need not be limited to the explicitly shown steps or units, and can include steps or units not explicitly shown for these processes, methods, products or devices, or other steps or units inherent to them.

[0020] First, some of the nouns or terms that appear in the description of the embodiments of the present application are interpreted as follows.

[0021] Intermittent production process: Also referred to as a batch production process. It means that all work steps are performed at the same location at different times, the operating state is unstable, and the parameters change over time. For example, raw material batches are put into the equipment, operated, and the products are discharged, and then the equipment is cleaned, new materials are put in, and it is repeated many times.

[0022] Operation trajectory: A trajectory generated by the change of operation parameters over time.

[0023] In related technologies, the standard curve of the operating trajectory is extremely important, and it is only meaningful to adjust based on a good standard curve of the operating trajectory. On the other hand, the conventional generation of standard curves of operating trajectories is generally done manually, and such methods are somewhat subjective. Moreover, a single, fixed method of generating a standard curve of the operating trajectory cannot adequately adapt to successive changes in production equipment and changes in production needs.

[0024] To address the above-mentioned problems, the embodiments of this application provide corresponding solutions, which are described in detail below.

[0025] Embodiments of the method for determining an operation trajectory curve provided in the embodiments of the present application can be implemented in a mobile terminal, a computer terminal, or a similar computing device. Figure 1 shows a hardware configuration block diagram of a computer terminal (or electronic device) that implements the method for determining an operation trajectory curve. As shown in Figure 1, the computer terminal 10 (or electronic device 10) may include one or more processors (indicated in the figure as 102a, 102b, ..., 102n) (the processors may include, but are not limited to, processing units such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 configured to store data, and a transmission module 106 configured to have communication functions. In addition to these, it may further include a display, an input / output interface (I / O interface), a general-purpose serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply, and / or a camera. It will be understood by those skilled in the art that the configuration shown in Figure 1 is schematic and not limited to the configuration of the electronic device. For example, the computer terminal 10 may include more or fewer components than those shown in Figure 1, or may have a different configuration than that shown in Figure 1.

[0026] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to as “data processing circuits” in this specification. These data processing circuits can be embodied in whole or in part as software, hardware, firmware, or any other combination. Furthermore, a data processing circuit may be a single, independent processing module, or it may be combined in whole or in part with any one of the other elements in the computer terminal 10 (or electronic device). As referred to in the embodiments of this application, this data processing circuit, as a processor, controls, for example, the selection of paths for variable resistor terminals connected to an interface.

[0027] Memory 104 may be configured to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the method for determining the operation trajectory curve in the embodiment of the present application, and the processor executes various functional applications and data processing by executing the software programs and modules stored in memory 104, that is, realizes the method for determining the operation trajectory curve described above. Memory 104 may include high-speed random access memory and may further include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid memory. In some examples, memory 104 may further include memory located remotely from the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, intranet, local area network, mobile communication network, and combinations thereof.

[0028] The transmission module 106 is configured to send and receive data over a network. Specific examples of the network described above include a wireless network provided by the communication vendor of the computer terminal 10. In one example, the transmission module 106 includes a network interface controller (NIC) that is connected to other network devices via a base station and can communicate with the internet. In another example, the transmission module 106 may be a radio frequency (RF) module configured to communicate with the internet wirelessly.

[0029] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or electronic device).

[0030] In some optional embodiments, the computer equipment (or electronic device) shown in Figure 1 above may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware and software elements. Please note that Figure 1 is merely one example of a specific example and is intended to illustrate the types of components that may be present in the computer equipment (or electronic device) described above.

[0031] In the operating environment described above, an embodiment of the method for determining the operation trajectory curve is provided in the embodiment of the present invention. The steps shown in the flowchart of the drawings may be executed in a computer system of a series of computer-executable instructions, and although the flowchart shows a logical order, the steps shown or described may be executed in an order different from the order shown herein.

[0032] Figure 2 is a flowchart of the method for determining the operation trajectory curve according to an embodiment of the present invention, and as shown in Figure 2, this method includes the following steps.

[0033] In step S202, operational data and output data are acquired for multiple batches of production equipment. The operational data is collected by different meters, and the output data is product data about the products produced by the production equipment, with each of the multiple batches corresponding to a different collection date.

[0034] In an optional embodiment, the operational data may include process data such as pressure, temperature, and flow rate, and this operational data constantly changes at different times; for example, the operational data may be collected once every second. The output data may include, for example, yield, energy consumption per unit, and the percentage of high-quality products, and the output data for the same batch will be the same. Note that the data included in the operational data and output data described above are merely examples, and other data will also be included in the actual production process, but these will not be explained in detail here.

[0035] In step S204, a join operation is performed on operational and production data corresponding to the same collection date in multiple batches to obtain a joined dataset.

[0036] Before combining the data in step S204 above, data preprocessing is performed on the acquired operational data and output data to process outliers, missing values, etc. After data preprocessing, operational data and output data from multiple batches with the same collection date are combined, that is, operational data from the same time according to the operating time are aligned and combined with output data from the same collection date (i.e., the same batch) to obtain the combined operational / output dataset.

[0037] In step S206, the similarity between the joined data in the combined dataset is determined, the joined data in the combined dataset is classified according to the similarity, and data with a similarity greater than a predetermined threshold is classified into one class, resulting in multiple classes of data.

[0038] In step S206 described above, data in the combined dataset whose similarity is greater than a predetermined threshold are classified into one class using a clustering algorithm, such as the K-means algorithm, and after clustering, data of multiple classes is obtained.

[0039] In step S208, data of a target type is selected from multiple classes of data, weight values ​​corresponding to different batches of operational parameters in the data of the target type are determined, where the data of the target type is data from any of the multiple classes of data, and the operational parameters are at least one controllable data from the operational data.

[0040] In step S208 above, for data of multiple classes, class-centric data for each class is selected as a representative of that class, i.e., an example. The examples are then labeled, for example, as low-energy consumption examples, high-yield examples, high-quality examples, etc., and the collection of multiple examples forms an example library. From the example library, one type of example containing n batches of data is selected, that is, data of the target type is selected from the data of multiple classes, and weight values ​​corresponding to the operation parameters of different batches in the data of the target type are determined.

[0041] In step S208 above, the operating parameter is at least one controllable data from the operating data. For example, if the operating data includes pressure, temperature, and flow rate, and the flow rate is adjustable by a valve, then the flow rate can be one of the operating parameters. However, if the pressure and temperature are not adjustable, then the pressure and temperature cannot be used as operating parameters.

[0042] In step S210, the operation trajectory curve corresponding to the target type data is determined, at least according to the weight values ​​and the values ​​of the operation parameters in the batch corresponding to the weight values.

[0043] In the embodiment of this invention, operational data and output data are collected from different batches, and abnormal values, missing values, etc., in the data are processed by data preprocessing to improve the accuracy of the system in drawing operation trajectory curves. Furthermore, operational and output data from different batches are combined by data integration to obtain operational and output datasets. In addition, similar operational and output data in the operational and output datasets are classified using a clustering algorithm to obtain cases. Cases are then labeled to form a case library, and the weight of each batch within the selected cases is calculated to calculate a standard curve of operation trajectory. This makes it possible to automatically generate a standard curve of operation trajectory according to production needs targets without human intervention.

[0044] In step S204 of the method for determining the operation trajectory curve described above, the step of performing a join operation on operational data and production data corresponding to the same collection date in multiple batches specifically includes the steps of obtaining the operating time corresponding to the operational data, aligning the operational data having the same operating time and sorting them according to the operating time to obtain first data, joining the first data with production data corresponding to the same collection date to obtain joined data, and determining joined data corresponding to different collection dates to obtain a joined dataset.

[0045] In the embodiment of this invention, the intermittent production process is batch production, and the operational data for each batch has two dimensions: a variable and time, i.e., the value of the operational data and the operational time. However, the output data has only one dimension. Therefore, when establishing an operational-output dataset, it is necessary to combine the operational data and output data of one batch into a single operational-output dataset. This will be explained with the following example.

[0046] The operational and output data for a particular batch are shown in Table 1.

[0047] (Table 1) Operation and output data for one batch TIFF0007835883000001.tif87170

[0048] Using a clustering algorithm, operational and production data in the combined dataset whose similarity exceeds a predetermined threshold are clustered into a single class. This yields data from several classes, i.e., multiple classes, and class-centered data from each class are selected as representative examples. Table 2 shows examples obtained after clustering in the combined dataset.

[0049] (Table 2) Examples obtained after clustering of combined datasets TIFF0007835883000002.tif117170

[0050] After labeling the generated examples above, we obtain something like Table 3.

[0051] (Table 3) Examples of labeling TIFF0007835883000003.tif112170

[0052] In step S208 of the method for determining the operation trajectory curve described above, the step of determining weight values ​​corresponding to different batches of operation parameters in the target type data specifically includes the steps of obtaining collection dates corresponding to different batches of operation parameters in the target type data to obtain multiple collection dates, sorting the multiple collection dates in order of proximity to the current date to obtain a target collection date set, and determining weight values ​​for batches corresponding to multiple collection dates in the target collection date set.

[0053] In the above step, the step of determining the batch weight values ​​corresponding to multiple collection dates in the target collection date set is, specifically, the step of determining the weight values ​​between batches corresponding to two adjacent dates in the target collection date set, wherein the weight of the batch corresponding to the first of the two adjacent dates is a predetermined multiple of the weight of the batch corresponding to the second date, the first date is the one of the two adjacent dates closer to the current date, the second date is the one of the two adjacent dates further from the current date, and the predetermined multiple is any value greater than 1.

[0054] In the embodiment of this application, batches are sorted in order of proximity to the current time. It is assumed that the weight of batches closer to the current time is 1.5 times that of batches slightly further away from the current time. This 1.5 corresponds to the above-mentioned preset multiple, which can be any number greater than 1. The selected preset multiple may be the same or different across different batches, and the specific number selected may be set by the user according to the actual situation. If k1 is the weight of the batch furthest from the current time, then k2 = 1.5k1, k3 = 1.5k2 = 1.5 2 k1…, k n =1.5 n-1 When k1 is obtained and the sum of all weights is set to 1, the following occurs: k1+1.5k1+1.5 2 k1+ … +1.5 n-1 k1=1 Solving k1 gives k2, k3, ... k n This can be obtained.

[0055] In the above step, after determining the weight values ​​between batches corresponding to two adjacent dates in the target collection date set, the method further includes the steps of: obtaining a weight set for batches corresponding to all dates in the target collection date set; constructing an equation according to the numerical relationships between all weight values ​​in the weight set; and solving the equation to obtain a first weight value between batches corresponding to two adjacent dates in the target collection date set.

[0056] In the embodiment of the present application, data of a target type is selected from data of a plurality of classes. For example, data of a low energy consumption case in Table 3 is selected. Assume that, as shown in Tables 4 and 5, the low energy consumption case includes operation / output data of 4 batches.

[0057] (Table 4) Batch data included in the low energy consumption case TIFF0007835883000004.tif92170

[0058] (Table 5) Batch data included in the low energy consumption case (continued) TIFF0007835883000005.tif90170

[0059] If k1 is set as the weight of the batch farthest from the current time, under the condition that "the weight closer to the current time is 1.5 times the weight farther from the current time", k2 = 1.5k1, k3 = 1.5k2 = 1.5 2 k1, k4 = 1.5k 3= 1.5 3 becomes k1, and when the sum of all weights is set to 1, the following equation can be obtained. k1 + 1.5k1 + 1.5 2 k1 + 1.5 3 k1 = 1

[0060] Solving this gives k1 = 0.123, k2 = 0.185, k3 = 0.277, and k4 = 0.415. The obtained values correspond to the first weight values described above.

[0061] In step S210 of the method for determining the operation trajectory curve described above, the step of determining the operation trajectory curve corresponding to data of the target type specifically includes the step of determining the target weight value of a batch corresponding to each date in the target collection date set according to a first weight value, and the step of determining the target operation parameter according to the target weight value and the value of the operation parameter at different operating times of the batch corresponding to the target weight value, wherein the target operation parameter is the value of the operation parameter at different operating times of the operation trajectory curve corresponding to data of the target type.

[0062] In the embodiment of the present invention, the values ​​of the operation parameters at each time point in the standard curve of the operation trajectory are calculated as follows: TIFF0007835883000006.tif23170

[0063] Here, s p,t This is the value of the operation parameter p at time t in the operation trajectory curve, and x p,i,t is the value of the operation parameter p at time t in the i-th batch, and k i This is the weight of the i-th batch.

[0064] In an optional example, if the above low-energy consumption case includes four batches of operational and production data, and assuming the current date is May 1, 2022, batch 1 is the furthest from the current date and has the smallest corresponding weight. Thus, the value of operation parameter 1 at hour 1 of the operation trajectory is as follows: k4*28.8+k3*22.5+k2*24+k1*25=0.415*28.8+0.277*22.5+0.185*24+0.123*25=25.7

[0065] Calculate operation parameters 2 to n using the method described above, and similarly calculate operation parameters 1 to n for hours 2 to m using the method described above.

[0066] In the method for determining the operation trajectory curve described above, the operation trajectory curve is a curve in a coordinate system established with the operating time as the horizontal coordinate and the values ​​of the operation parameters during the operating time as the vertical coordinate.

[0067] In the embodiment of this invention, the weighted average value of each operation parameter at each time point is calculated using batch weights, and these weighted average values ​​are concatenated to obtain a standard curve of the operation trajectory.

[0068] In this application, for intermittent production scenarios in process industries, a standard curve of the operation trajectory is generated from multiple optimal batches according to the production goals to be achieved by analyzing the operation data of historical batches and the output data of the final product. The method for determining the operation trajectory curve provided in the embodiment of this application has the following advantages: 1. There is no need to manually create the standard curve of the operation trajectory in advance. 2. Cases are obtained using actual historical data, and these cases are used as the basis for creating the standard curve of the operation trajectory. 3. Considering that batches closer to the current time have greater reference value, a method for calculating the weights of different batches in the same class of cases is designed. 4. The standard curve of the operation trajectory is obtained from the weighted average of different batches in the same class of cases.

[0069] Figure 3 is a configuration diagram of an operation trajectory curve determination device according to an embodiment of the present invention. As shown in Figure 3, the device comprises an acquisition module 302, a coupling module 304, a classification module 306, a first determination module 308, and a second determination module 310.

[0070] The acquisition module 302 is configured to acquire operational data and output data for multiple batches of production equipment. The operational data is data collected by different meters, and the output data is product data about products produced by the production equipment, with each of the multiple batches corresponding to a different collection date.

[0071] The merging module 304 is configured to perform a merge operation on operational and production data corresponding to the same collection date in multiple batches to obtain a merged dataset.

[0072] The classification module 306 is configured to determine the similarity between joined data in a combined dataset, classify the joined data in the combined dataset according to the similarity, and obtain data in multiple classes, where data with a similarity greater than a pre-set threshold is classified into one class.

[0073] The first decision module 308 is configured to select target type data from multiple classes of data and to determine weight values ​​corresponding to different batches of operational parameters in the target type data, where the target type data is data from any of the multiple classes of data, and the operational parameters are at least one controllable data from the operational data.

[0074] The second decision module 310 is configured to determine an operation trajectory curve corresponding to data of a target type, according to at least the weight values ​​and the values ​​of the operation parameters in the batch corresponding to the weight values.

[0075] Since the device for determining the operation trajectory curve shown in Figure 3 is configured to execute the method for determining the operation trajectory curve shown in Figure 2, the relevant explanation of the method for determining the operation trajectory curve also applies to this device, and therefore, the explanation is omitted here.

[0076] In an embodiment of the present invention, a non-volatile storage medium containing a stored computer program, wherein the equipment on which the non-volatile storage medium is located executes the computer program to acquire operational data and output data for multiple batches of production equipment, wherein the operational data is data collected by different meters, and the output data is product data relating to products produced in the production equipment, and each of the multiple batches corresponds to a different collection date; a join operation is performed on the operational data and output data corresponding to the same collection date in the multiple batches to obtain a joined dataset; and the similarity between the joined data in the joined dataset is determined, and the joined data in the joined dataset is classified according to the similarity. A non-volatile storage medium is further provided that performs a method for determining an operation trajectory curve, which includes the steps of: obtaining multiple classes of data by classifying data whose similarity is greater than a preset threshold into one class; selecting target type data from the multiple classes of data and determining weight values ​​corresponding to different batch operation parameters in the target type data, wherein the target type data is data from any of the multiple classes of data, and the operation parameters are at least one controllable data from the operational data; and determining an operation trajectory curve corresponding to the target type data according to at least the weight values ​​and the values ​​of the operation parameters in the batch corresponding to the weight values.

[0077] The above-mentioned examples of the present invention are for illustrative purposes only and do not indicate any indication of superiority or inferiority among the examples.

[0078] In the embodiments described above, each embodiment has its own emphasis, and for parts not explained in detail in one embodiment, you can refer to the relevant descriptions in other embodiments.

[0079] In some embodiments provided herein, it should be understood that the disclosed technical content may be realized in other forms. The embodiments of the apparatus described above are illustrative only, and for example, the division of the units may be logic-functional divisions, and other divisional forms may be possible in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not performed. Also, the coupling or direct coupling or communication connection between the shown or discussed components may be indirect coupling or communication connection through some interface, unit or module, and may be electrical or in other forms.

[0080] The unit described as a separating member may or may not be physically separate, and the member indicated as a unit may or may not be a physical unit, that is, it may be located in one place or distributed among multiple units. Depending on the actual needs, some or all of the units can be selected to achieve the objectives of the embodiment.

[0081] Furthermore, each functional unit in each embodiment of the present application may be integrated into a single processing unit, individual units may exist physically independently, and two or more units may be integrated into a single unit. The integrated unit may be implemented in hardware form or in the form of a software functional unit.

[0082] When the integrated unit described above is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored on a single computer-readable storage medium. Based on such understanding, the essence of the technical aspects of the present application, or parts that contribute to the prior art, or all or part of such technical aspects, may be implemented in the form of a software product, which is stored on a storage medium containing a plurality of instructions that cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The storage medium described above includes various media capable of storing program code, such as USB drives, read-only memory (ROM), random access memory (RAM), portable hard disks, magnetic disks, or optical disks.

[0083] The foregoing describes only preferred embodiments of the present application; however, a person skilled in the art could make several improvements and modifications without departing from the principles of the present application, and these improvements and modifications should also be within the scope of protection of the present application. [Industrial applicability]

[0084] The technical embodiments provided in the present invention can be applied to the field of production design in process industries. In the embodiments of the present invention, operational data and output data are acquired from multiple batches of production equipment, a join operation is performed on the operational data and output data corresponding to the same collection date in the multiple batches to obtain a join dataset, the similarity between the join data in the join dataset is determined, the join data in the join dataset is classified according to the similarity to obtain multiple classes of data, target type data is selected from the multiple classes of data, weight values ​​corresponding to the operational parameters of different batches in the target type data are determined, and an operation trajectory curve corresponding to the target type data is determined according to at least the weight values ​​and the values ​​of the operational parameters in the batches corresponding to the weight values, thereby achieving the objective of automatically generating operation trajectories during production and realizing a technical effect that improves the efficiency of operation trajectory generation. Furthermore, the conventional generation of standard curves for operation trajectories is generally done manually, which solves the problem that it cannot adapt to gradual changes in production equipment or changes in production needs.

Claims

1. A step of acquiring operational data and output data for multiple batches of production equipment, wherein the operational data is data collected by different meters, the output data is product data relating to products produced by the production equipment, and each of the multiple batches corresponds to a different collection date. The steps include performing a join operation on operational data and production data corresponding to the same collection date in the aforementioned multiple batches to obtain a joined dataset, The steps include determining the similarity between the joined data in the combined dataset, classifying the joined data in the combined dataset according to the similarity, and obtaining multiple classes of data by classifying data whose similarity is greater than a predetermined threshold into one class, A step of selecting target type data from the plurality of classes of data, and determining weight values ​​corresponding to different batches of operation parameters in the target type data, wherein the target type data is data from any of the plurality of classes of data, and the operation parameter is at least one controllable data from the operation data; The steps of determining an operation trajectory curve corresponding to data of the target type according to the weight value and the value of the operation parameter in the batch corresponding to the weight value, wherein the operation trajectory curve is a curve in a coordinate system established with the operating time as the horizontal coordinate and the value of the operation parameter in the operating time as the vertical coordinate, Includes, The step of determining weight values ​​corresponding to different batch operation parameters in the target type data includes the steps of obtaining collection dates corresponding to different batch operation parameters in the target type data to obtain a plurality of collection dates, sorting the plurality of collection dates in order of proximity to the current date to obtain a target collection date set, and determining weight values ​​for batches corresponding to the plurality of collection dates in the target collection date set. A method for determining an operation trajectory curve, comprising the step of determining the weight values ​​of batches corresponding to multiple collection dates in the target collection date set, the step of determining the weight values ​​between batches corresponding to two adjacent dates in the target collection date set, wherein the weight of the batch corresponding to the first of the two adjacent dates is the weight of the batch corresponding to the second date multiplied by a predetermined multiple, the first date is the one of the two adjacent dates that is closer to the current date, the second date is the one of the two adjacent dates that is further from the current date, and the predetermined multiple is any value greater than 1.

2. The step of performing a join operation on operational data and production data corresponding to the same collection date in the aforementioned multiple batches is: The steps include obtaining the operating time corresponding to the aforementioned operating data, The steps include aligning operational data with the same operating time, sorting them according to the operating time, and obtaining first data, The steps include: combining the first data and the production data corresponding to the same collection date to obtain the combined data; The method according to claim 1, comprising the steps of determining combined data corresponding to different collection dates and obtaining the combined dataset.

3. After determining the weight values ​​between batches corresponding to two adjacent dates in the target collection date set, The steps include obtaining a set of batch weights corresponding to all dates in the target collection date set, The steps include constructing an equation according to the numerical relationships between all the weight values ​​in the aforementioned weight set, The method according to claim 1, further comprising the step of solving the equation to obtain a first weight value between batches corresponding to two adjacent dates in the target collection date set.

4. The step of determining the operation trajectory curve corresponding to the data of the aforementioned target type is: The steps include determining the target weight value for the batch corresponding to each date in the target collection date set according to the first weight value, The method according to claim 3, comprising the step of determining a target operation parameter according to the target weight value and the value of the operation parameter at different operating times of a batch corresponding to the target weight value, wherein the target operation parameter is the value of the operation parameter at different operating times of an operation trajectory curve corresponding to data of the target type.

5. An acquisition module configured to acquire operational data and output data in multiple batches of production equipment, wherein the operational data is data collected by different meters, the output data is product data relating to products produced in the production equipment, and each of the multiple batches corresponds to a different collection date. A join module configured to perform a join operation on operational data and production data corresponding to the same collection date in the aforementioned multiple batches to obtain a joined dataset, A classification module is configured to determine the similarity between joined data in the combined dataset, classify the joined data in the combined dataset according to the similarity, and obtain multiple classes of data where the similarity is greater than a preset threshold, and A first decision module configured to select target type data from a plurality of classes of data and to determine weight values ​​corresponding to different batches of operation parameters in the target type data, wherein the target type data is data from any of the plurality of classes of data, and the operation parameters are at least one controllable data from the operation data. A second decision module configured to determine an operation trajectory curve corresponding to data of the target type according to the weight values ​​and the values ​​of the operation parameters in the batch corresponding to the weight values, wherein the operation trajectory curve is a curve in a coordinate system established with operating time as the horizontal coordinate and the values ​​of the operation parameters in the operating time as the vertical coordinate. Equipped with, Determining weight values ​​corresponding to different batch operation parameters in the target type data includes obtaining collection dates corresponding to different batch operation parameters in the target type data to obtain multiple collection dates, sorting the multiple collection dates in order of proximity to the current date to obtain a target collection date set, and determining weight values ​​for batches corresponding to multiple collection dates in the target collection date set. An operation trajectory curve determination device, which includes determining the weight values ​​of batches corresponding to multiple collection dates in the target collection date set, which means determining the weight values ​​between batches corresponding to two adjacent dates in the target collection date set, wherein the weight of the batch corresponding to the first of the two adjacent dates is the weight of the batch corresponding to the second date multiplied by a predetermined multiple, the first date is the one of the two adjacent dates that is closer to the current date, the second date is the one of the two adjacent dates that is further from the current date, and the predetermined multiple is any value greater than 1.

6. Memory configured to store program instructions, A processor connected to the memory, the processor is The system acquires operational data and output data for multiple batches of production equipment, wherein the operational data is collected by different meters, the output data is product data relating to products produced by the production equipment, and each of the multiple batches corresponds to a different collection date. A join operation is performed on the operational data and production data corresponding to the same collection date in the aforementioned multiple batches to obtain a joined dataset. The similarity between the joined data in the combined dataset is determined, the joined data in the combined dataset is classified according to the similarity, and data with a similarity greater than a predetermined threshold is classified into one class, thereby obtaining multiple classes of data. Select target type data from the aforementioned multiple classes of data, determine weight values ​​corresponding to different batch operation parameters in the target type data, wherein the target type data is data from one of the aforementioned multiple classes of data, and the operation parameter is at least one controllable data from the operational data. At a minimum, the system is configured to execute program instructions that realize a function, determining an operation trajectory curve corresponding to data of the target type according to the weight value and the value of the operation parameter in the batch corresponding to the weight value, wherein the operation trajectory curve is a curve in a coordinate system established with the operating time as the horizontal coordinate and the value of the operation parameter in the operating time as the vertical coordinate. Determining weight values ​​corresponding to different batch operation parameters in the target type data includes obtaining collection dates corresponding to different batch operation parameters in the target type data to obtain multiple collection dates, sorting the multiple collection dates in order of proximity to the current date to obtain a target collection date set, and determining weight values ​​for batches corresponding to multiple collection dates in the target collection date set. An electronic device comprising determining the weight values ​​of batches corresponding to multiple collection dates in the target collection date set, which means determining the weight values ​​between batches corresponding to two adjacent dates in the target collection date set, wherein the weight of the batch corresponding to the first of the two adjacent dates is the weight of the batch corresponding to the second date multiplied by a predetermined multiple, the first date is the one of the two adjacent dates that is closer to the current date, the second date is the one of the two adjacent dates that is further from the current date, and the predetermined multiple is any value greater than 1.

7. A non-volatile storage medium containing a stored computer program, wherein the device on which the non-volatile storage medium is located executes the method for determining the operation trajectory curve described in any one of claims 1 to 4 by executing the computer program.

Images