Industrial brain cloud control method and system of artificial intelligence integrated platform

Abstract

The invention discloses an industrial brain cloud control method and system of an artificial intelligence integrated platform, and relates to the field of industrial automation, and the method comprises the steps: carrying out the construction of an industrial knowledge model; constructing a production process energy consumption model; preliminary production parameters are obtained; obtaining target production parameters; establishing a production quality evaluation standard; the target production parameters are used for controlling the industrial production line, and production results at the basic nodes in the industrial production line are obtained; carrying out fault or flaw identification; when the fault exists, the fault existing in the industrial production line is processed; and when the flaws exist, optimizing the target production parameters to obtain production optimization parameters, and using the production optimization parameters to control the industrial production line. By arranging the model construction module, the parameter optimization module and the judgment and recognition module, under the condition that the quality is guaranteed, the energy consumption of the whole industrial production line is as low as possible, and the production line can be controlled with an accurate matching degree.

Description

Technical Field

[0001] The present invention relates to the field of industrial automation, and in particular to an industrial brain cloud control method and system for an artificial intelligence integrated platform. Background Art

[0002] The Industrial Brain is an intelligent system that integrates cutting-edge technologies such as artificial intelligence, big data, and cloud computing. It aims to realize real-time data collection and analysis of various links such as production equipment, process flow, and supply chain, so as to achieve comprehensive intelligent management of industrial production and provide enterprises with accurate decision-making support and optimization solutions.

[0003] Although the existing industrial brain control method can perform basic control of the production line, it lacks consideration of the energy consumption of the production line parameter settings. At the same time, due to the complexity of the production line, when anomalies occur, the solution is not well matched. Summary of the invention

[0004] In order to solve the above technical problems, an industrial brain cloud control method and system for an artificial intelligence integrated platform are provided. This technical solution solves the problems raised in the above background technology.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An industrial brain cloud control method for an artificial intelligence integrated platform, comprising:

[0007] Obtain an industrial production line controlled by an artificial intelligence platform and obtain the target products to be produced by the industrial production line;

[0008] Build industrial knowledge models based on industrial production lines;

[0009] Based on the industrial knowledge model, at least one basic node is set in the industrial production line, and the production process energy consumption model is constructed based on the industrial production line;

[0010] Based on the industrial knowledge model, the parameters of the industrial production line are set and debugged to obtain preliminary production parameters;

[0011] Based on the production process energy consumption model, the preliminary production parameters are optimized to obtain the target production parameters;

[0012] Establish production quality evaluation standards;

[0013] Use target production parameters to control industrial production lines and obtain production results at basic nodes in the industrial production lines;

[0014] Identify faults or defects based on production results and production quality evaluation criteria;

[0015] When a fault occurs, the operation of the industrial production line is stopped, the fault is fed back to the maintenance personnel, and the fault in the industrial production line is handled;

[0016] When defects exist, the target production parameters are optimized to obtain the production optimization parameters, and the production optimization parameters are used to control the industrial production line.

[0017] Preferably, the construction of the industrial knowledge model based on the industrial production line includes the following steps:

[0018] Acquire at least one industrial device used in an industrial production line, and acquire at least one industrial product to be produced by the industrial production line, wherein the target product is one of the industrial products;

[0019] Obtain the purpose of use of industrial equipment and the process effects produced by the purpose of use;

[0020] The process effects of industrial equipment are divided into difference effects and homogeneous effects, wherein the intersection of the difference effects of industrial equipment and the process effects of the remaining industrial equipment is empty, and the difference effects of industrial equipment are included in the process effects of the remaining industrial equipment;

[0021] Based on big data, the production process of industrial products is obtained, and the production process is decomposed based on the difference effect. The processes in the production process that are consistent with the difference effect are summarized as the first basic link, and the first basic link is paired with the corresponding industrial product;

[0022] Pair the industrial equipment corresponding to the difference effect with the first basic link;

[0023] The process of the production process of the industrial product sandwiched by the adjacent first basic link is taken as the second basic link, and the second basic link is paired with the corresponding industrial product;

[0024] Acquire a first basic link adjacent to the second basic link as a characteristic first basic link;

[0025] Determine whether the homogeneity effect of the industrial equipment corresponding to the first basic link of the feature is consistent with the effect of the second basic link. If so, allocate the industrial equipment corresponding to the first basic link of the feature to the second basic link. If not, do nothing.

[0026] The pairing relationship between the first basic link, the second basic link, industrial products and industrial equipment is used as the industrial knowledge model.

[0027] Preferably, the step of setting at least one basic node in the industrial production line based on the industrial knowledge model comprises the following steps:

[0028] Obtain at least one production indicator of the target product and obtain a normal value range of the production indicator;

[0029] Acquire at least one abnormal situation of the target product, and in the at least one abnormal situation, calculate the ratio of the production indicator deviating from the normal value range as an important index of the production indicator;

[0030] The production indicators whose important index is greater than the preset value are regarded as important production indicators;

[0031] The first basic link and the second basic link corresponding to the target product are respectively used as the target basic links;

[0032] The basic target links that have an impact on important production indicators will be taken as basic nodes.

[0033] Preferably, the construction of the production process energy consumption model based on the industrial production line includes the following steps:

[0034] The first basic link and the second basic link that affect the production index are obtained as characteristic basic links, respectively, wherein the target basic link and the basic node are both one of the characteristic basic links;

[0035] The parameter changes of the basic links of the characteristics are preset to obtain the indicated change value of the production index;

[0036] Accumulate the change values ​​of the indications corresponding to all the basic links of the characteristics to obtain the total indications;

[0037] The result of dividing the change value of the indication by the total of the indications is taken as the distribution coefficient of the basic link of the characteristic;

[0038] The normal value range of the production index is divided at equal intervals to obtain at least one identification point;

[0039] The value at the identification point is multiplied by the allocation coefficient to obtain the index allocation value of the basic link of the feature;

[0040] The parameter with the minimum energy consumption used by the industrial equipment corresponding to the basic link of the characteristic to produce the target product to achieve the index allocation value is used as the characteristic parameter;

[0041] The value at the identification point is paired with the characteristic parameter of the characteristic basic link and fitted to obtain the energy consumption fitting function, wherein the energy consumption fitting function is paired with the characteristic basic link, the value at the identification point is the independent variable, and the characteristic parameter is the dependent variable;

[0042] The energy consumption fitting function of at least one characteristic basic link constitutes the production process energy consumption model.

[0043] Preferably, the step of setting and debugging parameters of the industrial production line to obtain preliminary production parameters comprises the following steps:

[0044] The parameters of the industrial equipment corresponding to the basic links of the characteristics are randomly set to obtain the initial production parameters;

[0045] The initial production parameters are adjusted and tested until the initial production parameters satisfy the production index of the target product produced by the industrial production line and the indications are within the normal value range of the production index. The initial production parameters finally adjusted are used as preliminary production parameters.

[0046] Preferably, the step of optimizing the preliminary production parameters to obtain the target production parameters comprises the following steps:

[0047] The energy consumption fitting function of at least one characteristic basic link corresponding to the production index is superimposed to obtain a comprehensive energy consumption function;

[0048] In the normal value range of the production index, the minimum value of the comprehensive energy consumption function is obtained, and the indication of the production index corresponding to the minimum value of the comprehensive energy consumption function is taken as the target indication;

[0049] Substitute the target indication into the energy consumption fitting function of the characteristic basic link to obtain the target parameter of the characteristic basic link, and pair the target parameter with the industrial equipment corresponding to the characteristic basic link;

[0050] Obtain the initial parameters of industrial equipment under the initial production parameter settings;

[0051] When the gap between the initial parameters of the industrial equipment and the target parameters corresponding to the industrial equipment is greater than the preset gap, the initial parameters of the industrial equipment are optimized to the target parameters corresponding to the industrial equipment, otherwise, no processing is performed;

[0052] When the preliminary production parameter optimization is completed, the target production parameters are obtained, wherein the target production parameters are composed of the optimized parameters of all industrial equipment.

[0053] Preferably, the establishment of production quality evaluation standards includes the following steps:

[0054] Use the normal value range of important production indicators as the defect judgment standard;

[0055] At the basic node, the abnormal value range of important production indicators under the fault condition of the industrial production line is obtained as the fault judgment standard;

[0056] The defect judgment criteria and failure judgment criteria are summarized as the production quality evaluation criteria.

[0057] Preferably, the fault or defect identification based on the production results and the production quality evaluation criteria comprises the following steps:

[0058] In the production results, obtain the actual values ​​of important production indicators of the target product;

[0059] When the actual values ​​of the important production indicators are within the normal value range of the important production indicators, there is no fault or defect in the industrial production line. Otherwise, the important production indicators whose actual values ​​are not within the abnormal value range are obtained as characteristic important production indicators;

[0060] When the actual values ​​of the characteristic important production indicators do not fall within the abnormal value range of the characteristic important production indicators, the industrial production line has defects, otherwise the industrial production line has faults.

[0061] Preferably, the step of optimizing the target production parameters to obtain the production optimization parameters comprises the following steps:

[0062] The portion of the actual value of the characteristic important production index that exceeds the normal value range of the characteristic important production index is obtained as the amount to be adjusted;

[0063] Obtain the basic nodes that affect the important production indicators of the feature as the basic nodes of the feature;

[0064] The allocation coefficient of the characteristic basic node is multiplied by the amount to be adjusted to obtain the allocation amount to be adjusted;

[0065] Substitute the allocation amount to be adjusted into the energy consumption fitting function corresponding to the characteristic basic node to obtain the parameter adjustment amount;

[0066] The parameter adjustment amount is used to adjust the optimized parameters of the industrial equipment corresponding to the characteristic basic node to obtain the production optimization parameters.

[0067] An industrial brain cloud control system of an artificial intelligence integrated platform, used to implement the industrial brain cloud control method of the artificial intelligence integrated platform, comprising:

[0068] A data acquisition module, wherein the data acquisition module acquires the industrial production line controlled by the artificial intelligence platform and acquires the target product to be produced by the industrial production line;

[0069] A model building module, wherein the model building module builds an industrial knowledge model based on the industrial production line, sets at least one basic node in the industrial production line based on the industrial knowledge model, and builds a production process energy consumption model based on the industrial production line;

[0070] A parameter debugging module, which performs parameter setting and parameter debugging on the industrial production line based on the industrial knowledge model to obtain preliminary production parameters;

[0071] A parameter optimization module, wherein the parameter optimization module optimizes preliminary production parameters based on a production process energy consumption model to obtain target production parameters;

[0072] A standard establishment module, wherein the standard establishment module establishes production quality evaluation standards;

[0073] A result acquisition module, which uses the target production parameters to control the industrial production line and obtains the production results at basic nodes in the industrial production line;

[0074] A judgment and identification module, wherein the judgment and identification module identifies faults or defects based on production results and production quality evaluation standards;

[0075] A processing module, when a fault occurs, stops the operation of the industrial production line, feeds back the fault to maintenance personnel, processes the fault in the industrial production line, optimizes target production parameters when defects occur, obtains production optimization parameters, and uses the production optimization parameters to control the industrial production line.

[0076] Compared with the prior art, the present invention has the following beneficial effects:

[0077] By setting up the model building module, parameter optimization module and judgment and identification module, the quality of the target product to be produced can be taken into consideration when setting parameters. At the same time, the production parameters can be set as reasonably as possible while ensuring the quality, so that the energy depletion of the entire industrial production line can be as low as possible. In addition, considering that the changing conditions in the industrial production line may have unexpected effects on production, the production process is inspected, and the places that have a greater impact on quality are monitored. According to the monitoring results, fault handling is carried out, or production optimization parameters are used to control the industrial production line. In this way, the production line can be controlled with precise matching, thereby ensuring the quality of the products produced. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 It is a flow chart of the industrial brain cloud control method of the artificial intelligence integrated platform of the present invention;

[0079] Figure 2 It is a schematic diagram of the process of constructing an industrial knowledge model based on an industrial production line of the present invention;

[0080] Figure 3 A schematic diagram of a process of setting at least one basic node in an industrial production line based on an industrial knowledge model of the present invention;

[0081] Figure 4 It is a schematic diagram of the process of constructing a production process energy consumption model based on an industrial production line of the present invention;

[0082] Figure 5 A schematic diagram of the process of setting and debugging parameters of an industrial production line to obtain preliminary production parameters according to the present invention;

[0083] Figure 6 A schematic diagram of a process for optimizing preliminary production parameters to obtain target production parameters according to the present invention;

[0084] Figure 7 A schematic diagram of a process for establishing a production quality evaluation standard of the present invention;

[0085] Figure 8 A schematic diagram of a process for identifying faults or defects based on production results and production quality evaluation criteria of the present invention;

[0086] Fig. 9 The present invention is a flow chart of optimizing the target production parameters to obtain the production optimization parameters. DETAILED DESCRIPTION

[0087] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0088] Reference Figure 1 As shown, an industrial brain cloud control method of an artificial intelligence integrated platform includes:

[0089] Obtain an industrial production line controlled by an artificial intelligence platform and obtain the target products to be produced by the industrial production line;

[0090] Build industrial knowledge models based on industrial production lines;

[0091] Based on the industrial knowledge model, at least one basic node is set in the industrial production line, and the production process energy consumption model is constructed based on the industrial production line;

[0092] Based on the industrial knowledge model, the parameters of the industrial production line are set and debugged to obtain preliminary production parameters;

[0093] Based on the production process energy consumption model, the preliminary production parameters are optimized to obtain the target production parameters;

[0094] Establish production quality evaluation standards;

[0095] Use target production parameters to control industrial production lines and obtain production results at basic nodes in the industrial production lines;

[0096] Identify faults or defects based on production results and production quality evaluation criteria;

[0097] When a fault occurs, the operation of the industrial production line is stopped, the fault is fed back to the maintenance personnel, and the fault in the industrial production line is handled;

[0098] When defects exist, the target production parameters are optimized to obtain the production optimization parameters, and the production optimization parameters are used to control the industrial production line.

[0099] In this solution, the industrial knowledge model is constructed to distinguish the industrial equipment in the industrial production line, and then different settings can be made according to the different industrial products to ensure that their quality and energy consumption are controlled. Here, the industrial production line can produce a variety of industrial products. Therefore, when the target product is produced, the participating industrial equipment may be part of the industrial production line;

[0100] In addition, since industrial production lines are affected by many factors, when industrial production lines operate according to target production parameters, the products produced may also have quality problems, so secondary adjustments are required.

[0101] Reference Figure 2 As shown, based on the industrial production line, the construction of the industrial knowledge model includes the following steps:

[0102] Acquire at least one industrial device used in an industrial production line, and acquire at least one industrial product to be produced by the industrial production line, wherein the target product is one of the industrial products;

[0103] Obtain the purpose of use of industrial equipment and the process effects produced by the purpose of use;

[0104] The process effects of industrial equipment are divided into difference effects and homogeneous effects, wherein the intersection of the difference effects of industrial equipment and the process effects of the remaining industrial equipment is empty, and the difference effects of industrial equipment are included in the process effects of the remaining industrial equipment;

[0105] Based on big data, the production process of industrial products is obtained, and the production process is decomposed based on the difference effect. The processes in the production process that are consistent with the difference effect are summarized as the first basic link, and the first basic link is paired with the corresponding industrial product;

[0106] Pair the industrial equipment corresponding to the difference effect with the first basic link;

[0107] The process of the production process of the industrial product sandwiched by the adjacent first basic link is taken as the second basic link, and the second basic link is paired with the corresponding industrial product;

[0108] Acquire a first basic link adjacent to the second basic link as a characteristic first basic link;

[0109] Determine whether the homogeneity effect of the industrial equipment corresponding to the first basic link of the feature is consistent with the effect of the second basic link. If so, allocate the industrial equipment corresponding to the first basic link of the feature to the second basic link. If not, do nothing.

[0110] The pairing relationship between the first basic link, the second basic link, industrial products and industrial equipment is used as the industrial knowledge model.

[0111] The purpose of the industrial knowledge model is to determine the industrial equipment used in each link of the production process of industrial products, so that the target product can be called to obtain the required industrial equipment and then perform subsequent parameter settings;

[0112] There are homogeneity and differences in the process effects of industrial equipment. Therefore, based on the difference part, the first basic link in the production process of industrial products is first obtained. Since the production process of industrial products is continuous, the process sandwiched by adjacent first basic links must be completed by the industrial equipment corresponding to the adjacent first basic links. However, since there are two industrial equipment, it is necessary to determine whether the homogeneous effect of the industrial equipment corresponding to the characteristic first basic link is consistent with the effect of the second basic link, thereby determining the industrial equipment corresponding to the second basic link.

[0113] Reference Figure 3 As shown, based on the industrial knowledge model, setting at least one basic node in the industrial production line includes the following steps:

[0114] Obtain at least one production indicator of the target product and obtain a normal value range of the production indicator;

[0115] Acquire at least one abnormal situation of the target product, and in the at least one abnormal situation, calculate the ratio of the production indicator deviating from the normal value range as an important index of the production indicator;

[0116] The production indicators whose important index is greater than the preset value are regarded as important production indicators;

[0117] The first basic link and the second basic link corresponding to the target product are respectively used as the target basic links;

[0118] The basic target links that have an impact on important production indicators will be taken as basic nodes.

[0119] Basic nodes are used to control quality. Basic nodes are the target basic links that affect important production indicators. This is because many links are involved in the production of target products, but most of the links have little impact on quality. Unless there are major problems, they will not affect the quality. Major problems must be solved manually. Therefore, unimportant links are not monitored, which can reduce the workload of monitoring.

[0120] Reference Figure 4 As shown, based on the industrial production line, the construction of the production process energy consumption model includes the following steps:

[0121] The first basic link and the second basic link that affect the production index are obtained as characteristic basic links, respectively, wherein the target basic link and the basic node are both one of the characteristic basic links;

[0122] The parameter changes of the basic links of the characteristics are preset to obtain the indicated change value of the production index;

[0123] Accumulate the change values ​​of the indications corresponding to all the basic links of the characteristics to obtain the total indications;

[0124] The result of dividing the change value of the indication by the total of the indications is taken as the distribution coefficient of the basic link of the characteristic;

[0125] The normal value range of the production index is divided at equal intervals to obtain at least one identification point;

[0126] The value at the identification point is multiplied by the allocation coefficient to obtain the index allocation value of the basic link of the feature;

[0127] The parameter with the minimum energy consumption used by the industrial equipment corresponding to the basic link of the characteristic to produce the target product to achieve the index allocation value is used as the characteristic parameter;

[0128] The value at the identification point is paired with the characteristic parameter of the characteristic basic link and fitted to obtain the energy consumption fitting function, wherein the energy consumption fitting function is paired with the characteristic basic link, the value at the identification point is the independent variable, and the characteristic parameter is the dependent variable;

[0129] The energy consumption fitting function of at least one characteristic basic link constitutes the production process energy consumption model.

[0130] The production index may be determined by multiple production links. Therefore, it is necessary to form an energy consumption fitting function for each associated characteristic basic link. The energy consumption fitting function is used to form the parameters of industrial equipment that meet the production index requirements.

[0131] Here it is necessary to assign weights to the numerical values ​​of the production indicators, and the weight is the distribution coefficient, because the contribution of each link to the production indicators is different.

[0132] Reference Figure 5 As shown, setting and debugging parameters of the industrial production line to obtain preliminary production parameters includes the following steps:

[0133] The parameters of the industrial equipment corresponding to the basic links of the characteristics are randomly set to obtain the initial production parameters;

[0134] The initial production parameters are adjusted and tested until the initial production parameters satisfy the production index of the target product produced by the industrial production line and the indications are within the normal value range of the production index. The initial production parameters finally adjusted are used as preliminary production parameters.

[0135] Reference Figure 6 As shown, optimizing the preliminary production parameters to obtain the target production parameters includes the following steps:

[0136] The energy consumption fitting function of at least one characteristic basic link corresponding to the production index is superimposed to obtain a comprehensive energy consumption function;

[0137] In the normal value range of the production index, the minimum value of the comprehensive energy consumption function is obtained, and the indication of the production index corresponding to the minimum value of the comprehensive energy consumption function is taken as the target indication;

[0138] Substitute the target indication into the energy consumption fitting function of the characteristic basic link to obtain the target parameter of the characteristic basic link, and pair the target parameter with the industrial equipment corresponding to the characteristic basic link;

[0139] Obtain the initial parameters of industrial equipment under the initial production parameter settings;

[0140] When the gap between the initial parameters of the industrial equipment and the target parameters corresponding to the industrial equipment is greater than the preset gap, the initial parameters of the industrial equipment are optimized to the target parameters corresponding to the industrial equipment, otherwise, no processing is performed;

[0141] When the preliminary production parameter optimization is completed, the target production parameters are obtained, wherein the target production parameters are composed of the optimized parameters of all industrial equipment.

[0142] Since the energy consumption fitting functions are different, it is impossible to ensure that the values ​​of the production indicators make the energy consumption of all associated characteristic basic links the lowest. Therefore, a compromise method is adopted to set the values ​​of the production indicators so that the total energy consumption of all associated characteristic basic links is the lowest.

[0143] According to the above description, the optimized parameters of the industrial equipment may be target parameters or initial parameters.

[0144] Reference Figure 7 As shown, establishing production quality evaluation standards includes the following steps:

[0145] Use the normal value range of important production indicators as the defect judgment standard;

[0146] At the basic node, the abnormal value range of important production indicators under the fault condition of the industrial production line is obtained as the fault judgment standard;

[0147] The defect judgment criteria and failure judgment criteria are summarized as the production quality evaluation criteria.

[0148] Reference Figure 8 As shown, based on the production results and production quality evaluation criteria, fault or defect identification includes the following steps:

[0149] In the production results, obtain the actual values ​​of important production indicators of the target product;

[0150] When the actual values ​​of the important production indicators are within the normal value range of the important production indicators, there is no fault or defect in the industrial production line. Otherwise, the important production indicators whose actual values ​​are not within the abnormal value range are obtained as characteristic important production indicators;

[0151] When the actual values ​​of the characteristic important production indicators do not fall within the abnormal value range of the characteristic important production indicators, the industrial production line has defects, otherwise the industrial production line has faults.

[0152] The difference between products caused by defects and faults in industrial production lines is obvious. Therefore, production quality evaluation standards can be set to distinguish between the two and make corresponding optimizations accordingly.

[0153] Reference Fig. 9 As shown, optimizing the target production parameters to obtain the production optimization parameters includes the following steps:

[0154] The portion of the actual value of the characteristic important production index that exceeds the normal value range of the characteristic important production index is obtained as the amount to be adjusted;

[0155] Obtain the basic nodes that affect the important production indicators of the feature as the basic nodes of the feature;

[0156] The allocation coefficient of the characteristic basic node is multiplied by the amount to be adjusted to obtain the allocation amount to be adjusted;

[0157] Substitute the allocation amount to be adjusted into the energy consumption fitting function corresponding to the characteristic basic node to obtain the parameter adjustment amount;

[0158] The parameter adjustment amount is used to adjust the optimized parameters of the industrial equipment corresponding to the characteristic basic node to obtain the production optimization parameters.

[0159] During optimization, the different contributions of different characteristic basic nodes to the characteristic important production indicators are also taken into account. Therefore, the amount to be adjusted is weighted and distributed, so that each characteristic basic node is adjusted differently;

[0160] Here, when making adjustments, it is necessary to determine the correlation between the parameter adjustment amount and the characteristic important production indicators. When it is positively correlated, the optimized parameters of the industrial equipment corresponding to the characteristic basic node need to be reduced by the parameter adjustment amount. When it is negatively correlated, the optimized parameters of the industrial equipment corresponding to the characteristic basic node need to be increased by the parameter adjustment amount.

[0161] An industrial brain cloud control system of an artificial intelligence integrated platform, used to implement the industrial brain cloud control method of the artificial intelligence integrated platform, comprising:

[0162] A data acquisition module, wherein the data acquisition module acquires the industrial production line controlled by the artificial intelligence platform and acquires the target product to be produced by the industrial production line;

[0163] A model building module, wherein the model building module builds an industrial knowledge model based on the industrial production line, sets at least one basic node in the industrial production line based on the industrial knowledge model, and builds a production process energy consumption model based on the industrial production line;

[0164] A parameter debugging module, which performs parameter setting and parameter debugging on the industrial production line based on the industrial knowledge model to obtain preliminary production parameters;

[0165] A parameter optimization module, wherein the parameter optimization module optimizes preliminary production parameters based on a production process energy consumption model to obtain target production parameters;

[0166] A standard establishment module, wherein the standard establishment module establishes production quality evaluation standards;

[0167] A result acquisition module, which uses the target production parameters to control the industrial production line and obtains the production results at basic nodes in the industrial production line;

[0168] A judgment and identification module, wherein the judgment and identification module identifies faults or defects based on production results and production quality evaluation standards;

[0169] A processing module, when a fault occurs, stops the operation of the industrial production line, feeds back the fault to maintenance personnel, processes the fault in the industrial production line, optimizes target production parameters when defects occur, obtains production optimization parameters, and uses the production optimization parameters to control the industrial production line.

[0170] Furthermore, the present solution also proposes a storage medium on which a computer-readable program is stored, and when the computer-readable program is called, the industrial brain cloud control method of the above-mentioned artificial intelligence integrated platform is executed.

[0171] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0172] To sum up, the advantages of the present invention are: by setting a model building module, a parameter optimization module and a judgment and identification module, the quality of the target product produced can be taken into consideration when setting parameters. At the same time, while ensuring the quality, the production parameters can be set as reasonably as possible, so that the energy depletion of the entire industrial production line may be as low as possible, and considering that the changeable conditions in the industrial production line may have unexpected effects on production, the production process is detected, and the places that have a greater impact on the quality are monitored. According to the monitoring results, fault handling is performed, or production optimization parameters are used to control the industrial production line. Thus, the production line can be controlled with precise matching, thereby ensuring that the quality of the products produced is guaranteed.

[0173] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An industrial brain cloud control method for an artificial intelligence integrated platform, characterized in that: include: Obtain an industrial production line controlled by an artificial intelligence platform and obtain the target products to be produced by the industrial production line; Build industrial knowledge models based on industrial production lines; Based on the industrial knowledge model, at least one basic node is set in the industrial production line, and the production process energy consumption model is constructed based on the industrial production line; Based on the industrial knowledge model, the parameters of the industrial production line are set and debugged to obtain preliminary production parameters; Based on the production process energy consumption model, the preliminary production parameters are optimized to obtain the target production parameters; Establish production quality evaluation standards; Use target production parameters to control industrial production lines and obtain production results at basic nodes in the industrial production lines; Identify faults or defects based on production results and production quality evaluation criteria; When a fault occurs, the operation of the industrial production line is stopped, the fault is fed back to the maintenance personnel, and the fault in the industrial production line is handled; When defects exist, the target production parameters are optimized to obtain the production optimization parameters, and the production optimization parameters are used to control the industrial production line.

2. The industrial brain cloud control method of an artificial intelligence integrated platform according to claim 1 is characterized in that: The construction of the industrial knowledge model based on the industrial production line includes the following steps: Acquire at least one industrial device used in an industrial production line, and acquire at least one industrial product to be produced by the industrial production line, wherein the target product is one of the industrial products; Obtain the purpose of use of industrial equipment and the process effects produced by the purpose of use; The process effects of industrial equipment are divided into difference effects and homogeneous effects, wherein the intersection of the difference effects of industrial equipment and the process effects of the remaining industrial equipment is empty, and the difference effects of industrial equipment are included in the process effects of the remaining industrial equipment; Based on big data, the production process of industrial products is obtained, and the production process is decomposed based on the difference effect. The processes in the production process that are consistent with the difference effect are summarized as the first basic link, and the first basic link is paired with the corresponding industrial product; Pair the industrial equipment corresponding to the difference effect with the first basic link; The process of the production process of the industrial product sandwiched by the adjacent first basic link is taken as the second basic link, and the second basic link is paired with the corresponding industrial product; Acquire a first basic link adjacent to the second basic link as a characteristic first basic link; Determine whether the homogeneity effect of the industrial equipment corresponding to the first basic link of the feature is consistent with the effect of the second basic link. If so, allocate the industrial equipment corresponding to the first basic link of the feature to the second basic link. If not, do nothing. The pairing relationship between the first basic link, the second basic link, industrial products and industrial equipment is used as the industrial knowledge model.

3. The industrial brain cloud control method of an artificial intelligence integrated platform according to claim 2 is characterized in that: The step of setting at least one basic node in an industrial production line based on the industrial knowledge model comprises the following steps: Obtain at least one production indicator of the target product and obtain a normal value range of the production indicator; Acquire at least one abnormal situation of the target product, and in the at least one abnormal situation, calculate the ratio of the production indicator deviating from the normal value range as an important index of the production indicator; The production indicators whose important index is greater than the preset value are regarded as important production indicators; The first basic link and the second basic link corresponding to the target product are respectively used as the target basic links; The basic target links that have an impact on important production indicators will be taken as basic nodes.

4. The industrial brain cloud control method of an artificial intelligence integrated platform according to claim 3 is characterized in that: The construction of the production process energy consumption model based on the industrial production line includes the following steps: The first basic link and the second basic link that affect the production index are obtained as characteristic basic links, respectively, wherein the target basic link and the basic node are both one of the characteristic basic links; The parameter changes of the basic links of the characteristics are preset to obtain the indicated change value of the production index; Accumulate the change values ​​of the indications corresponding to all the basic links of the characteristics to obtain the total indications; The result of dividing the change value of the indication by the total of the indications is taken as the distribution coefficient of the basic link of the characteristic; The normal value range of the production index is divided at equal intervals to obtain at least one identification point; The value at the identification point is multiplied by the allocation coefficient to obtain the index allocation value of the basic link of the feature; The parameter with the minimum energy consumption used by the industrial equipment corresponding to the basic link of the characteristic to produce the target product to achieve the index allocation value is used as the characteristic parameter; The value at the identification point is paired with the characteristic parameter of the characteristic basic link and fitted to obtain the energy consumption fitting function, wherein the energy consumption fitting function is paired with the characteristic basic link, the value at the identification point is the independent variable, and the characteristic parameter is the dependent variable; The energy consumption fitting function of at least one characteristic basic link constitutes the production process energy consumption model.

5. The industrial brain cloud control method of an artificial intelligence integrated platform according to claim 4 is characterized in that: The parameter setting and parameter debugging of the industrial production line to obtain preliminary production parameters includes the following steps: The parameters of the industrial equipment corresponding to the basic links of the characteristics are randomly set to obtain the initial production parameters; The initial production parameters are adjusted and tested until the initial production parameters satisfy the production index of the target product produced by the industrial production line and the indications are within the normal value range of the production index. The initial production parameters finally adjusted are used as preliminary production parameters.

6. The industrial brain cloud control method and system of an artificial intelligence integrated platform according to claim 5 is characterized in that: The optimization of the preliminary production parameters to obtain the target production parameters comprises the following steps: The energy consumption fitting function of at least one characteristic basic link corresponding to the production index is superimposed to obtain a comprehensive energy consumption function; In the normal value range of the production index, the minimum value of the comprehensive energy consumption function is obtained, and the indication of the production index corresponding to the minimum value of the comprehensive energy consumption function is taken as the target indication; Substitute the target indication into the energy consumption fitting function of the characteristic basic link to obtain the target parameter of the characteristic basic link, and pair the target parameter with the industrial equipment corresponding to the characteristic basic link; Obtain the initial parameters of industrial equipment under the initial production parameter settings; When the gap between the initial parameters of the industrial equipment and the target parameters corresponding to the industrial equipment is greater than the preset gap, the initial parameters of the industrial equipment are optimized to the target parameters corresponding to the industrial equipment, otherwise, no processing is performed; When the preliminary production parameter optimization is completed, the target production parameters are obtained, wherein the target production parameters are composed of the optimized parameters of all industrial equipment.

7. The industrial brain cloud control method of an artificial intelligence integrated platform according to claim 6 is characterized in that: The establishment of production quality evaluation standards comprises the following steps: Use the normal value range of important production indicators as the defect judgment standard; At the basic node, the abnormal value range of important production indicators under the fault condition of the industrial production line is obtained as the fault judgment standard; The defect judgment criteria and failure judgment criteria are summarized as the production quality evaluation criteria.

8. The industrial brain cloud control method of an artificial intelligence integrated platform according to claim 7 is characterized in that: The fault or defect identification based on the production results and the production quality evaluation standard comprises the following steps: In the production results, obtain the actual values ​​of important production indicators of the target product; When the actual values ​​of the important production indicators are within the normal value range of the important production indicators, there is no fault or defect in the industrial production line. Otherwise, the important production indicators whose actual values ​​are not within the abnormal value range are obtained as characteristic important production indicators; When the actual values ​​of the characteristic important production indicators do not fall within the abnormal value range of the characteristic important production indicators, the industrial production line has defects, otherwise the industrial production line has faults.

9. The industrial brain cloud control method of an artificial intelligence integrated platform according to claim 8 is characterized in that: Optimizing the target production parameters to obtain the production optimization parameters comprises the following steps: The portion of the actual value of the characteristic important production index that exceeds the normal value range of the characteristic important production index is obtained as the amount to be adjusted; Obtain the basic nodes that affect the important production indicators of the feature as the basic nodes of the feature; The allocation coefficient of the characteristic basic node is multiplied by the amount to be adjusted to obtain the allocation amount to be adjusted; Substitute the allocation amount to be adjusted into the energy consumption fitting function corresponding to the characteristic basic node to obtain the parameter adjustment amount; The parameter adjustment amount is used to adjust the optimized parameters of the industrial equipment corresponding to the characteristic basic node to obtain the production optimization parameters.

10. An industrial brain cloud control system of an artificial intelligence integrated platform, used to implement the industrial brain cloud control method of an artificial intelligence integrated platform as described in any one of claims 1 to 9, characterized in that: include: A data acquisition module, wherein the data acquisition module acquires the industrial production line controlled by the artificial intelligence platform and acquires the target product to be produced by the industrial production line; A model building module, wherein the model building module builds an industrial knowledge model based on the industrial production line, sets at least one basic node in the industrial production line based on the industrial knowledge model, and builds a production process energy consumption model based on the industrial production line; A parameter debugging module, which performs parameter setting and parameter debugging on the industrial production line based on the industrial knowledge model to obtain preliminary production parameters; A parameter optimization module, wherein the parameter optimization module optimizes preliminary production parameters based on a production process energy consumption model to obtain target production parameters; A standard establishment module, wherein the standard establishment module establishes production quality evaluation standards; A result acquisition module, which uses the target production parameters to control the industrial production line and obtains the production results at basic nodes in the industrial production line; A judgment and identification module, wherein the judgment and identification module identifies faults or defects based on production results and production quality evaluation standards; A processing module, when a fault occurs, stops the operation of the industrial production line, feeds back the fault to maintenance personnel, processes the fault in the industrial production line, optimizes target production parameters when defects occur, obtains production optimization parameters, and uses the production optimization parameters to control the industrial production line.

Images