Production management system and method of special sealing primer for wet base plane

Abstract

The invention relates to the field of intelligent production management, in particular to a production management system and method of a special sealing primer for a wet base plane. The system comprises a raw material management module used for managing purchase, inventory and quality detection of raw materials; the production planning module is used for making a production plan and scheduling production resources; the production process control module is used for monitoring and controlling various parameters in the production process in real time; the quality control module is used for detecting and recording product quality; and the equipment maintenance module is used for managing the maintenance of the equipment. In the production process control module, the time sequence change trend of the temperature and the stirring speed is collected and monitored in real time, so that the stirring speed is dynamically adjusted to adapt to the real-time requirements of temperature change and other production conditions, human intervention is reduced, and the automation level of stirring speed control in the production process is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent production management, and in particular to a production management system and method for a special sealing primer for wet substrates. Background Art

[0002] With the continuous advancement of construction technology and industrial applications, the demand for sealers that can provide long-term durability and protection in humid environments has increased significantly. These specialized sealers are not only required to have fast drying and excellent adhesion, but also good chemical resistance and mechanical strength to withstand a variety of harsh environmental conditions.

[0003] In the production process of the special sealer for wet substrates, plasticizers need to be added to the heated epoxy resin and stirred to reduce the viscosity of the epoxy resin, increase its fluidity, and ensure that the plasticizer can be evenly dispersed, thereby improving the workability and construction performance of the final product.

[0004] However, the stirring speed control in the production process of traditional wet-surface special sealers often relies on the operator's experience and judgment, which lacks precision, which easily leads to uneven dispersion of plasticizers and affects the overall quality and performance of the product. In addition, manual control is difficult to adapt to real-time changes in the production process, such as temperature fluctuations, which may have an adverse effect on the performance of the final product.

[0005] Therefore, a production management system for a special sealer for wet substrates is desired. Summary of the invention

[0006] This application is made in consideration of the above problems. One purpose of this application is to provide a production management system and method for a special sealer for wet substrates.

[0007] The embodiment of the present application provides a production management system for a special sealing primer for a wet base surface, which includes: Raw materials management module, used to manage the procurement, inventory and quality inspection of raw materials; Production planning module, used to formulate production plans and dispatch production resources; Production process control module, used to monitor and control various parameters in the production process in real time; Quality control module, used to detect and record product quality; The equipment maintenance module is used to manage the maintenance and upkeep of equipment.

[0008] For example, according to the production management system of the wet base surface special sealing primer of the embodiment of the present application, the production process control module includes: The epoxy resin real-time temperature acquisition unit is used to acquire the time queue of the real-time temperature of the epoxy resin acquired by the temperature sensor; A real-time stirring speed acquisition unit, used to acquire a time queue of the real-time stirring speed acquired by the stirring speed monitor; A real-time parameter time scale segmentation unit, used for performing sequence segmentation on the time queue of the real-time temperature and the time queue of the real-time stirring speed based on the same time scale to obtain a sequence of local time series input vectors of the real-time temperature and a sequence of local time series input vectors of the real-time stirring speed; A real-time parameter time series propagation unit, used for inputting the sequence of the real-time temperature local time series input vector and the sequence of the real-time stirring speed local time series input vector into a feature forward propagation network based on significant time series attenuation of node energy to obtain a real-time temperature time series propagation representation vector and a stirring speed time series propagation representation vector; A real-time temperature-stirring speed aggregation unit, used for inputting the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector into a feature decoupling local interaction fine-grained aggregation module to obtain a real-time temperature-stirring speed decoupling enhanced interaction global representation vector as a real-time temperature-stirring speed decoupling enhanced interaction global representation feature; The stirring speed value control unit is used to obtain an optimization instruction based on the real-time temperature-stirring speed decoupling enhanced interaction global representation feature, and the optimization instruction is used to indicate whether the stirring speed value at the next time point should be increased, decreased or kept unchanged.

[0009] For example, according to the production management system of the special sealer for wet base surface according to the embodiment of the present application, the real-time parameter time series propagation unit includes: A real-time temperature local time series energy significant descriptor calculation subunit is used to calculate the energy significant descriptor of each real-time temperature local time series input vector in the sequence of the real-time temperature local time series input vector based on the mean and standard deviation of each real-time temperature local time series input vector to obtain a sequence of real-time temperature local time series energy significant descriptors; A timestamp extraction subunit, used for extracting the timestamp of each real-time temperature local time series input vector in the sequence of the real-time temperature local time series input vector to obtain a sequence of real-time temperature timestamps; A vector slicing subunit, used to use the real-time temperature local time series input vector corresponding to the current time point in the sequence of the real-time temperature local time series input vector as the current node feature vector and use the real-time temperature local time series input vectors corresponding to other time points as the historical node feature vectors to obtain a sequence of the current real-time temperature local time series input vector and the historical real-time temperature local time series input vector; A real-time temperature energy time decay factor calculation subunit, used to calculate the energy time decay factor of each historical real-time temperature local time series input vector in the sequence of the historical real-time temperature local time series input vector relative to the current real-time temperature local time series input vector to obtain a sequence of real-time temperature local time series energy time decay factors; A historical real-time temperature local time series propagation subunit, used to perform time series propagation aggregation on the sequence of the historical real-time temperature local time series input vectors using the sequence of the real-time temperature local time series energy significant descriptors as positive adjustment factors and the sequence of the real-time temperature local time series energy time decay factors as negative adjustment factors to obtain a historical real-time temperature local time series propagation aggregation representation feature vector; The fusion subunit is used to fuse the historical real-time temperature local time series propagation aggregation representation feature vector and the current real-time temperature local time series input vector to obtain the real-time temperature time series propagation representation vector.

[0010] For example, according to the production management system of the moist base surface special sealing agent of the embodiment of the present application, the real-time temperature local time series energy significant descriptor calculation subunit is used to: Respectively calculating the mean and standard deviation of the real-time temperature local time series input vector to obtain the real-time temperature local time series feature mean and the real-time temperature local time series feature standard deviation; Calculating the position difference between the real-time temperature local time series input vector and the real-time temperature local time series feature mean to obtain a real-time temperature local time series difference vector; Calculating the fourth power of each eigenvalue in the real-time temperature local time series difference vector to obtain a real-time temperature local time series modulation difference vector; Calculating the expected value of the real-time temperature local timing modulation difference vector to obtain the real-time temperature local timing expected value; The real-time temperature local time series expected value is divided by the fourth power of the real-time temperature local time series feature standard deviation to obtain the real-time temperature local time series energy significant descriptor.

[0011] For example, according to the production management system of the special sealing primer for wet base surface according to the embodiment of the present application, the real-time temperature energy time attenuation factor calculation subunit is used to: The real-time temperature timestamp corresponding to the current real-time temperature local time series input vector is subtracted from the real-time temperature timestamp corresponding to each historical real-time temperature local time series input vector, and then rounded down to obtain a sequence of historical real-time temperature time span values; After calculating the square of the positional division of the sequence of historical real-time temperature time span values ​​and the time attenuation inverse scaling parameter to obtain a sequence of historical real-time temperature time span square modulation values, the sequence of historical real-time temperature time span square modulation values ​​is positionally multiplied by the attenuation rate positive scaling parameter to obtain a sequence of real-time temperature time series span energy attenuation coefficients; Taking each real-time temperature time series span energy attenuation coefficient in the sequence of the real-time temperature time series span energy attenuation coefficient as an exponential power, a natural exponential function value with a natural constant e as a base is calculated to obtain a sequence of the real-time temperature local time series energy time attenuation factors.

[0012] For example, according to the production management system of the special sealing primer for wet base surfaces according to the embodiment of the present application, the historical real-time temperature local time series propagation subunit is used to: divide the sequence of the real-time temperature local time series energy significant descriptors by the sequence of the real-time temperature local time series energy time attenuation factors by position to obtain a sequence of real-time temperature adjustment factors, and calculate the position-weighted sum of the sequence of the real-time temperature adjustment factors and the sequence of the historical real-time temperature local time series input vectors to obtain the historical real-time temperature local time series propagation aggregation representation feature vector.

[0013] For example, according to the production management system of the special sealing primer for wet base surface according to the embodiment of the present application, the real-time temperature-stirring speed polymerization unit includes: A feature decoupling subunit, used for feature decoupling the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector to obtain a sequence of real-time temperature local time series propagation aggregation representation vectors and a sequence of stirring speed local time series propagation aggregation representation vectors; A real-time temperature-stirring speed local temporal sequence semantic association interaction subunit is used to calculate the local semantic association interaction vector between each corresponding group of real-time temperature local temporal sequence propagation aggregation representation vectors and stirring speed local temporal sequence propagation aggregation representation vectors in the sequence of real-time temperature local temporal sequence propagation aggregation representation vectors and the sequence of stirring speed local temporal sequence propagation aggregation representation vectors to obtain a sequence of real-time temperature-stirring speed local temporal sequence semantic association interaction vectors; A real-time temperature-stirring speed local temporal sequence fine-grained attention weight calculation subunit, used to calculate the fine-grained attention weight of each real-time temperature-stirring speed local temporal sequence semantic association interaction vector in the sequence of real-time temperature-stirring speed local temporal sequence semantic association interaction vectors to obtain a sequence of real-time temperature-stirring speed local temporal sequence fine-grained attention weights; A deactivation processing subunit, used for inputting the sequence of real-time temperature-stirring speed local time series fine-grained attention weights into a random deactivation module to obtain a sequence of real-time temperature-stirring speed local time series fine-grained attention weights after deactivation processing; A weighted sum calculation subunit, used to calculate the weighted sum of the sequence of real-time temperature-stirring speed local temporal fine-grained attention weights after the deactivation process as the weight distribution, to obtain the real-time temperature-stirring speed decoupling reinforcement interaction global representation vector; Wherein, the real-time temperature-stirring speed local time series fine-grained attention weight calculation subunit is used for: After multiplying each real-time temperature-stirring speed local time-series semantic association interaction vector in the sequence of real-time temperature-stirring speed local time-series semantic association interaction vectors by a weight matrix, the obtained vector is added to the bias vector by position to obtain a sequence of real-time temperature-stirring speed local time-series semantic association interaction modulation vectors; Inputting the sequence of real-time temperature-stirring speed local temporal semantic association interaction modulation vectors into a tanh function for activation processing to obtain a sequence of real-time temperature-stirring speed local temporal semantic association interaction activation vectors; Each real-time temperature-stirring speed local temporal sequence semantic association interaction activation vector in the sequence of the real-time temperature-stirring speed local temporal sequence semantic association interaction activation vector is multiplied by a weight coefficient vector to obtain a sequence of the real-time temperature-stirring speed local temporal sequence fine-grained attention weights.

[0014] For example, according to the production management system of the special sealing primer for wet base surface according to the embodiment of the present application, the real-time temperature-stirring speed local time sequence semantic association interaction sub-unit includes: Respectively calculating the position difference, position dot product and position addition between the real-time temperature local time series propagation aggregation representation vector and the stirring speed local time series propagation aggregation representation vector to obtain the real-time temperature-stirring speed local time series propagation aggregation difference vector, the real-time temperature-stirring speed local time series propagation aggregation dot product vector and the real-time temperature-stirring speed local time series propagation aggregation addition vector; The real-time temperature-stirring speed local time series propagation aggregate difference vector, the real-time temperature-stirring speed local time series propagation aggregate dot product vector and the real-time temperature-stirring speed local time series propagation aggregate sum vector are cascaded and then one-dimensional convolutional coding is performed to obtain a real-time temperature-stirring speed local time series multi-dimensional fusion vector; The real-time temperature-stirring speed local time series multi-dimensional fusion vector is subjected to a local window-based maximum pooling process to obtain the real-time temperature-stirring speed local time series semantic association interaction vector.

[0015] For example, according to the production management system of the special sealing primer for wet base surfaces according to the embodiment of the present application, the stirring speed value control unit is used to: input the real-time temperature-stirring speed decoupling reinforcement interaction global representation vector into the classifier-based stirring speed optimization module to obtain the optimization instruction, and the optimization instruction is used to indicate that the stirring speed value at the next time point should increase, decrease or remain unchanged.

[0016] The embodiment of the present application also provides a production management method of a special sealing primer for a wet base surface, which comprises: Manage the procurement, inventory and quality testing of raw materials; Formulate production plans and dispatch production resources; Real-time monitoring and control of various parameters in the production process; Test and record product quality; Manage the care and maintenance of equipment.

[0017] According to the production management system and method of the special sealing primer for wet base surfaces of the embodiment of the present application, in the production process control module, the temporal change trends of temperature and stirring speed are collected and monitored in real time, so as to dynamically adjust the stirring speed to adapt to the real-time needs of temperature changes and other production conditions, thereby reducing human intervention and improving the automation level of stirring speed control in the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.

[0019] Figure 1 It shows a structural schematic diagram of a production management system for a special sealing primer for a wet base surface in an embodiment of the present application; Figure 2 It shows a structural schematic diagram of a production process control module of a production management system for a special sealing primer for wet substrates in an embodiment of the present application; Figure 3 A flowchart showing a production management method of a special sealing primer for wet substrates in an embodiment of the present application; and Figure 4 An application scenario diagram of a production management system for a special sealing primer for wet substrates in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0021] The terms used in this specification are those common terms currently widely used in the art in consideration of the functions of the present application, but these terms may vary according to the intentions of those skilled in the art, precedents, or new technologies in the art. In addition, specific terms may be selected, and in this case, their detailed meanings will be described in the detailed description of the present application. Therefore, the terms used in the specification should not be understood as simple names, but rather as a general description based on the meaning of the terms and the present application.

[0022] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0023] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0024] In addition, the application architecture diagram in the embodiment of the present application is intended to more clearly illustrate the technical solution in the embodiment of the present application, and does not constitute a limitation on the technical solution provided in the embodiment of the present application. Of course, for other application architectures and business applications, the technical solution provided in the embodiment of the present application is also applicable to similar problems.

[0025] The following is a non-restrictive description of the production management system of the special sealing primer for wet substrates provided according to at least one embodiment of the present application through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also fall within the scope of protection of the present application.

[0026] Based on this, the present application proposes a production management system for a special sealing primer for a wet base surface, such as Figure 1As shown, it includes: a raw material management module 810, which is used to manage the purchase, inventory and quality inspection of raw materials; a production plan module 820, which is used to formulate production plans and dispatch production resources; a production process control module 830, which is used to monitor and control various parameters in the production process in real time; a quality control module 840, which is used to detect and record product quality; and an equipment maintenance module 850, which is used to manage the maintenance and care of equipment.

[0027] Correspondingly, in the above-mentioned production process control module, the technical concept of the present application is to collect the real-time temperature of the epoxy resin by a temperature sensor, and collect the real-time stirring speed by a stirring speed monitor, and use an artificial intelligence-based data analysis and processing algorithm to perform local time-series segmentation and propagation polymerization of the real-time temperature and the real-time stirring speed, so as to adaptively control the stirring speed value at the next time point according to the mutual polymerization interaction characteristics of the real-time temperature and the stirring speed in the time sequence. In this way, the time-series change trend of the temperature and stirring speed can be collected and monitored in real time, so as to dynamically adjust the stirring speed to adapt to the real-time needs of temperature changes and other production conditions, thereby reducing human intervention and improving the automation level of stirring speed control in the production process.

[0028] Accordingly, if Figure 2 As shown, the production process control module 830 includes: an epoxy resin real-time temperature acquisition unit 831, which is used to obtain the time queue of the real-time temperature of the epoxy resin collected by the temperature sensor; a real-time stirring speed acquisition unit 832, which is used to obtain the time queue of the real-time stirring speed collected by the stirring speed monitor; a real-time parameter time scale segmentation unit 833, which is used to sequence the time queue of the real-time temperature and the time queue of the real-time stirring speed based on the same time scale to obtain a sequence of real-time temperature local time series input vectors and a sequence of real-time stirring speed local time series input vectors; a real-time parameter time series propagation unit 834, which is used to propagate the sequence of the real-time temperature local time series input vectors and the sequence of the real-time stirring speed local time series input vectors. The sequence input is based on the feature forward propagation network of significant time-series attenuation of node energy to obtain the real-time temperature time-series propagation representation vector and the stirring speed time-series propagation representation vector; the real-time temperature-stirring speed aggregation unit 835 is used to input the real-time temperature time-series propagation representation vector and the stirring speed time-series propagation representation vector into the feature decoupling local interaction fine-grained aggregation module to obtain the real-time temperature-stirring speed decoupling enhanced interaction global representation vector as the real-time temperature-stirring speed decoupling enhanced interaction global representation feature; the stirring speed value control unit 836 is used to obtain the optimization instruction based on the real-time temperature-stirring speed decoupling enhanced interaction global representation feature, and the optimization instruction is used to indicate that the stirring speed value at the next time point should increase, decrease or remain unchanged.

[0029] Specifically, in the technical solution of the present application, first, the time queue of the real-time temperature of the epoxy resin collected by the temperature sensor is obtained, and the time queue of the real-time stirring speed collected by the stirring speed monitor is obtained. Then, considering the timing fluctuations and change rules of different local time segments in the time queue of the real-time temperature and the time queue of the real-time stirring speed, the parameter timing characteristic fluctuation pattern in each local time segment can be analyzed and understood more concentratedly and carefully. In the technical solution of the present application, the time queue of the real-time temperature and the time queue of the real-time stirring speed are sequentially segmented based on the same time scale to obtain a sequence of local timing input vectors of the real-time temperature and a sequence of local timing input vectors of the real-time stirring speed.

[0030] Then, considering that different local times in the sequence of the real-time temperature local time series input vector and the sequence of the real-time stirring speed local time series input vector have different degrees of time series significance features, these significant features are crucial for the subsequent control of the stirring speed. Therefore, in order to enable the network to focus on the parameter data of the recent time point and capture the latest production process changes, in the technical solution of the present application, the sequence of the real-time temperature local time series input vector and the sequence of the real-time stirring speed local time series input vector are input into the feature forward propagation network based on the significant time series attenuation of node energy to obtain the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector. That is, the feature forward propagation network based on the significant time series attenuation of node energy is a network structure that aggregates the forward propagation of the entire time domain by focusing on the energy distribution in each feature and based on the characteristics of energy continuously decaying over time. Take the sequence of the real-time temperature local time series input vector as an example. Specifically, first, the energy descriptor of each feature is obtained by quantifying the overall energy level of each feature based on the mean and standard deviation of each real-time temperature local time series input vector. Then, the timestamp of each feature is extracted to capture the time feature change information of the real-time temperature. Then, the node feature vector at the current time point in the sequence is regarded as the current node feature vector, and the others are regarded as historical node feature vectors to distinguish between the current and historical node feature vectors, providing a reference for time series propagation aggregation. Next, each energy time decay factor of each historical node feature vector relative to the current node feature vector is calculated. Subsequently, each energy time decay factor and the energy descriptor of each feature are used as reverse and forward adjustment factors to weighted aggregate the set of historical node feature vectors to reveal the propagation process of the feature in the time series, that is, as time goes by, the importance of early information gradually weakens, while the influence of recent information becomes more significant. Finally, the current node features and historical aggregation features are fused to obtain a real-time temperature time series propagation representation vector containing rich time series features.

[0031] Correspondingly, the real-time parameter timing propagation unit 834 includes: a real-time temperature local timing energy significant descriptor calculation subunit, which is used to calculate the energy significant descriptors of each real-time temperature local timing input vector based on the mean and standard deviation of each real-time temperature local timing input vector in the sequence of the real-time temperature local timing input vector to obtain a sequence of real-time temperature local timing energy significant descriptors; a timestamp extraction subunit, which is used to extract the timestamps of each real-time temperature local timing input vector in the sequence of the real-time temperature local timing input vector to obtain a sequence of real-time temperature timestamps; a vector slicing subunit, which is used to use the real-time temperature local timing input vector corresponding to the current time point in the sequence of the real-time temperature local timing input vector as the current node feature vector and use the real-time temperature local timing input vectors corresponding to other time points as the historical node feature vectors to obtain the current real-time temperature local timing input vector and the historical real-time temperature local timing input vector. A sequence of local time series input vectors; a real-time temperature energy time decay factor calculation subunit, used to calculate the energy time decay factor of each historical real-time temperature local time series input vector in the sequence of historical real-time temperature local time series input vectors relative to the current real-time temperature local time series input vector to obtain a sequence of real-time temperature local time series energy time decay factors; a historical real-time temperature local time series propagation subunit, used to use the sequence of real-time temperature local time series energy significant descriptors as a positive adjustment factor and the sequence of real-time temperature local time series energy time decay factors as a negative adjustment factor, and perform time series propagation aggregation on the sequence of historical real-time temperature local time series input vectors to obtain a historical real-time temperature local time series propagation aggregation representation feature vector; a fusion subunit, used to fuse the historical real-time temperature local time series propagation aggregation representation feature vector and the current real-time temperature local time series input vector to obtain the real-time temperature time series propagation representation vector.

[0032] Among them, the real-time temperature local timing series energy significant descriptor calculation subunit is used to: respectively calculate the mean and standard deviation of the real-time temperature local timing input vector to obtain the real-time temperature local timing feature mean and the real-time temperature local timing feature standard deviation; calculate the positional difference between the real-time temperature local timing input vector and the real-time temperature local timing feature mean to obtain the real-time temperature local timing difference vector; calculate the fourth power of each eigenvalue in the real-time temperature local timing difference vector to obtain the real-time temperature local timing modulation difference vector; calculate the expected value of the real-time temperature local timing modulation difference vector to obtain the real-time temperature local timing expected value; divide the real-time temperature local timing expected value by the fourth power of the real-time temperature local timing feature standard deviation to obtain the real-time temperature local timing significant descriptor.

[0033] Among them, the real-time temperature energy time attenuation factor calculation subunit is used to: subtract the real-time temperature timestamp corresponding to the current real-time temperature local time series input vector from the real-time temperature timestamp corresponding to each historical real-time temperature local time series input vector, and then round down to obtain a sequence of historical real-time temperature time span values; calculate the square of the sequence of historical real-time temperature time span values ​​divided by the time attenuation inverse scaling parameter to obtain a sequence of historical real-time temperature time span square modulation values, and then multiply the sequence of historical real-time temperature time span square modulation values ​​by the attenuation rate positive scaling parameter to obtain a sequence of real-time temperature time series span energy attenuation coefficients; use each real-time temperature time series span energy attenuation coefficient in the sequence of real-time temperature time series span energy attenuation coefficients as an exponential power, and calculate the natural exponential function value with the natural constant e as the base to obtain the sequence of real-time temperature local time series energy time attenuation factors.

[0034] Among them, the historical real-time temperature local time series propagation subunit is used to: divide the sequence of the real-time temperature local time series energy significant descriptors by the sequence of the real-time temperature local time series energy time attenuation factors by position to obtain a sequence of real-time temperature adjustment factors, and calculate the position-weighted sum of the sequence of the real-time temperature adjustment factors and the sequence of the historical real-time temperature local time series input vectors to obtain the historical real-time temperature local time series propagation aggregation representation feature vector.

[0035] In one example, the real-time parameter timing propagation unit 834 is used to: input the sequence of the real-time temperature local timing input vector into a feature forward propagation network based on the significant timing attenuation of node energy, and process it with the following forward propagation formula to obtain the real-time temperature timing propagation representation vector; wherein the forward propagation formula is: ;in, is a sequence of the real-time temperature local timing input vectors, and are the first and second order of the real-time temperature local timing input vector. and The real-time temperature local timing input vector, represents the number of feature vectors in the sequence of the real-time temperature local time series input vector, is the first in the sequence of the real-time temperature local timing input vector The characteristic value of each position in the local time series input vector of the real-time temperature, To calculate the expected value, and Respectively The mean and variance of the local time series input vector of real-time temperature, is the number of eigenvalues ​​in each real-time temperature local time series input vector, It is The energy-significant descriptor of the local time series input vector of real-time temperature, It is The energy-significant descriptor of the local time series input vector of real-time temperature, and Distribution represents and timestamp of the real-time temperature local timing input vector, To round down, is the time decay inverse scaling parameter, is the positive scaling parameter of the decay rate, and is the weight hyperparameter, represents the exponential function value with the natural constant e as the base, is the real-time temperature time series propagation representation vector. Similarly, the encoding method of the sequence of the real-time stirring speed local time series input vector is as shown in the above encoding.

[0036] Furthermore, it is considered that there are different degrees of interaction and interaction between the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector on the local time fine-grained scale. Therefore, in order to understand and consider each local time segment in a more fine-grained manner, in the technical solution of the present application, the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector are input into the feature decoupling local interaction fine-grained aggregation module to obtain the real-time temperature-stirring speed decoupling enhanced interaction global representation vector. In detail, first, the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector are feature decoupled to decompose the entire vector into a sequence with more local details and structure to obtain a sequence of real-time temperature local time series propagation aggregation representation vectors and a sequence of stirring speed local time series propagation aggregation representation vectors. Then, the local semantic interaction features between the corresponding local feature vectors in each group of local time series sequences are calculated to capture the local interaction between the real-time temperature and the stirring speed, that is, the mutual influence relationship at different time points. Furthermore, fine-grained attention weights are assigned to each local semantic interaction feature to obtain fine-grained attention weights for each real-time temperature-stirring speed local time series. These weights enhance the importance of the core elements in the interaction vector and guide the model to focus on the most critical feature interactions. Subsequently, each fine-grained attention weight is input into the random deactivation module for weight adjustment. That is, by randomly "closing" a part of the features, the model's sensitivity to key information can be increased. Finally, the weight sequence after deactivation is used as the weight distribution to perform weighted summation on each local semantic interaction feature to strengthen those local semantic interaction features with higher attention weights, while suppressing those features with lower weights, to achieve global interaction representation between local features, and obtain the real-time temperature-stirring speed decoupled enhanced interaction global representation vector.

[0037] Correspondingly, the real-time temperature-stirring speed aggregation unit 835 includes: a feature decoupling subunit, which is used to perform feature decoupling on the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector to obtain a sequence of real-time temperature local time series propagation aggregation representation vectors and a sequence of stirring speed local time series propagation aggregation representation vectors; a real-time temperature-stirring speed local time series semantic association interaction subunit, which is used to calculate the real-time temperature local time series propagation aggregation representation vector and the stirring speed local time series propagation aggregation representation vector in the sequence of the real-time temperature local time series propagation aggregation representation vector and the sequence of the stirring speed local time series propagation aggregation representation vector. The local semantic association interaction vectors between the real-time temperature and stirring speed local time series semantic association interaction vectors are used to obtain a sequence of real-time temperature-stirring speed local time series semantic association interaction vectors; a real-time temperature-stirring speed local time series fine-grained attention weight calculation subunit is used to calculate the fine-grained attention weights of each real-time temperature-stirring speed local time series semantic association interaction vector in the sequence of real-time temperature-stirring speed local time series semantic association interaction vectors to obtain a sequence of real-time temperature-stirring speed local time series fine-grained attention weights; an inactivation processing subunit is used to input the sequence of real-time temperature-stirring speed local time series fine-grained attention weights into a random inactivation module to obtain a real-time temperature-stirring speed local time series fine-grained attention weight after inactivation processing. A weighted sum calculation subunit is used to calculate the weighted sum of the sequence of real-time temperature-stirring speed local temporal fine-grained attention weights after the inactivation process as the weight distribution, and to calculate the weighted sum of the sequence of real-time temperature-stirring speed local temporal semantic association interaction vectors to obtain the real-time temperature-stirring speed decoupling reinforcement interaction global representation vector; wherein the real-time temperature-stirring speed local temporal fine-grained attention weight calculation subunit is used to: compare each real-time temperature-stirring speed local temporal semantic association interaction vector in the sequence of real-time temperature-stirring speed local temporal semantic association interaction vectors with the weight matrix After multiplication, the obtained vector is added to the bias vector by position to obtain a sequence of real-time temperature-stirring speed local temporal semantic association interaction modulation vectors; the sequence of real-time temperature-stirring speed local temporal semantic association interaction modulation vectors is input into the tanh function for activation processing to obtain a sequence of real-time temperature-stirring speed local temporal semantic association interaction activation vectors; each real-time temperature-stirring speed local temporal semantic association interaction activation vector in the sequence of real-time temperature-stirring speed local temporal semantic association interaction activation vectors is multiplied by the weight coefficient vector to obtain a sequence of real-time temperature-stirring speed local temporal fine-grained attention weights.

[0038] Among them, the real-time temperature-stirring speed local temporal sequence semantic association interaction subunit includes: respectively calculating the positional difference, positional dot multiplication and positional addition between the real-time temperature local temporal sequence propagation aggregation representation vector and the stirring speed local temporal sequence propagation aggregation representation vector to obtain the real-time temperature-stirring speed local temporal sequence propagation aggregation differential vector, the real-time temperature-stirring speed local temporal sequence propagation aggregation dot product vector and the real-time temperature-stirring speed local temporal sequence propagation aggregation sum vector; cascading the real-time temperature-stirring speed local temporal sequence propagation aggregation differential vector, the real-time temperature-stirring speed local temporal sequence propagation aggregation dot product vector and the real-time temperature-stirring speed local temporal sequence propagation aggregation sum vector, and performing one-dimensional convolution encoding to obtain the real-time temperature-stirring speed local temporal sequence multi-dimensional fusion vector; performing local window-based maximum pooling processing on the real-time temperature-stirring speed local temporal sequence multi-dimensional fusion vector to obtain the real-time temperature-stirring speed local temporal sequence semantic association interaction vector.

[0039] In a specific example, the real-time temperature-stirring speed aggregation unit 835 is used to: input the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector into the feature decoupling local interaction fine-grained aggregation module, and process them with the following interaction aggregation formula to obtain the real-time temperature-stirring speed decoupling enhanced interaction global representation vector; wherein the interaction aggregation formula is: ;in, and are respectively the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector, For feature decoupling operations, and are respectively the sequence of the real-time temperature local time series propagation aggregation representation vector and the sequence of the stirring speed local time series propagation aggregation representation vector. The real-time temperature local time series propagation aggregation representation vector and the The stirring speed local time series propagation aggregation represents the vector, represents the number of feature vectors in the sequence of the local time series propagation aggregation representation vector of the real-time temperature and the sequence of the local time series propagation aggregation representation vector of the stirring speed, and They are the real-time temperature local time series propagation aggregation representation vector and the stirring speed local time series propagation aggregation representation vector, and They are position difference, position dot multiplication and position addition respectively. For cascade processing, is a one-dimensional convolutional coding operation, is the maximum pooling operation, is the first in the sequence of the real-time temperature-stirring speed local temporal semantic association interaction vector A real-time temperature-stirring speed local temporal semantic association interaction vector, is the weight matrix, is the bias vector, is the tanh function, is the weight coefficient vector, is the first in the sequence of the real-time temperature-stirring speed local temporal fine-grained attention weights real-time temperature-stirring speed local temporal fine-grained attention weights, Indicates deactivation processing, is the first in the sequence of the real-time temperature-stirring speed local time series fine-grained attention weights after the deactivation process. The real-time temperature-stirring speed local time series fine-grained attention weight after deactivation processing, is the global representation vector of the real-time temperature-stirring speed decoupling reinforcement interaction.

[0040] Then, the real-time temperature-stirring speed decoupling enhanced interaction global representation vector is input into the classifier-based stirring speed optimization module to obtain an optimization instruction, and the optimization instruction is used to indicate whether the stirring speed value at the next time point should be increased, decreased, or kept unchanged. That is, the real-time temperature-stirring speed decoupling enhanced interaction global representation feature obtained by local fine-grained interaction using the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector is classified and processed to adaptively control the stirring speed value at the next time point. In this way, the temporal variation trend of temperature and stirring speed can be collected and monitored in real time, so as to dynamically adjust the stirring speed to adapt to the real-time needs of temperature changes and other production conditions, thereby reducing human intervention and improving the automation level of stirring speed control in the production process.

[0041] Correspondingly, the stirring speed value control unit 836 is used to: input the real-time temperature-stirring speed decoupling reinforcement interaction global representation vector into the classifier-based stirring speed optimization module to obtain the optimization instruction, and the optimization instruction is used to indicate that the stirring speed value at the next time point should increase, decrease or remain unchanged.

[0042] It should be understood that the role of the classifier is to use the given categories and known training data to learn classification rules and classifiers, and then classify (or predict) unknown data. Logistic regression, SVM, etc. are often used to solve binary classification problems. For multi-class classification problems, logistic regression or SVM can also be used, but multiple binary classifications are required to form a multi-classification, but this is prone to errors and inefficient. Commonly used multi-classification methods include the Softmax classification function.

[0043] In a preferred example, since the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector respectively represent the full-time domain time series forward propagation characteristics of the real-time temperature and the real-time stirring speed based on the significant attenuation of the energy of the time series nodes, when performing feature decoupled local interaction fine-grained aggregation on them, the fine-grained decoupled local interaction aggregation timing offset caused by the full-time domain feature distribution difference caused by the source time series distribution difference is taken into account, and it is expected to further improve the full-time domain fine-grained time series aggregation regression comprehensibility of the real-time temperature-stirring speed decoupling enhanced interaction global representation vector, thereby compensating for the lack of instance decision-making and improving the accuracy of the optimization instructions obtained by its input based on the classifier stirring speed optimization module.

[0044] Based on this, when the real-time temperature-stirring speed decoupling enhanced interaction global representation vector is input into the classifier-based stirring speed optimization module, the present application first optimizes the real-time temperature-stirring speed decoupling enhanced interaction global representation vector, including the steps of: Calculate the global representation vector of the real-time temperature-stirring speed decoupling enhancement interaction and The distance between eigenvalues, e.g. L 2 distance, and take the square root of the distance to obtain the global distance representation matrix of the real-time temperature-stirring speed decoupling reinforcement interaction, that is, ;in, represents the global representation vector of the real-time temperature-stirring speed decoupling enhancement interaction, and The first global representation vector of the real-time temperature-stirring speed decoupling enhancement interaction is represented by and Eigenvalues, The first global representation vector of the real-time temperature-stirring speed decoupling enhancement interaction is represented by and The distance between eigenvalues, Indicates the real-time temperature-stirring speed decoupling enhancement interaction global distance representation matrix The eigenvalue of the position; The real-time temperature-stirring speed decoupling and strengthening interaction global representation vector as a row vector is matrix-multiplied with the real-time temperature-stirring speed decoupling and strengthening interaction global distance representation matrix to obtain the real-time temperature-stirring speed decoupling and strengthening interaction global first-level mapping vector, that is, ;in, represents the global representation vector of the real-time temperature-stirring speed decoupling enhancement interaction, represents the transpose of a vector, represents matrix multiplication, Represents the global autocorrelation matrix of the real-time temperature-stirring speed decoupling reinforcement interaction; The real-time temperature-stirring speed decoupling enhancement interaction global autocorrelation matrix of the real-time temperature-stirring speed decoupling enhancement interaction global representation vector is obtained, that is, ;in, represents the global representation vector of the real-time temperature-stirring speed decoupling enhancement interaction, Represents the global distance representation matrix of the real-time temperature-stirring speed decoupling reinforcement interaction, represents matrix multiplication, Represents the global first-order mapping vector of the real-time temperature-stirring speed decoupling reinforcement interaction; The real-time temperature-stirring speed decoupling and strengthening interaction global first-level mapping vector is matrix-multiplied with the matrix product of the real-time temperature-stirring speed decoupling and strengthening interaction global distance representation matrix and the real-time temperature-stirring speed decoupling and strengthening interaction global autocorrelation matrix to obtain the real-time temperature-stirring speed decoupling and strengthening interaction global multi-level mapping vector ,in, represents the global first-level mapping vector of the real-time temperature-stirring speed decoupling enhancement interaction, Represents the global distance representation matrix of the real-time temperature-stirring speed decoupling reinforcement interaction, represents matrix multiplication, represents the global autocorrelation matrix of the real-time temperature-stirring speed decoupling reinforcement interaction, Represents the global multi-level mapping vector of real-time temperature-stirring speed decoupling reinforcement interaction; The real-time temperature-stirring speed decoupling and strengthening interaction global multi-level mapping vector is interpolated with the real-time temperature-stirring speed decoupling and strengthening interaction global correlation eigenvector composed of the eigenvalues ​​of the real-time temperature-stirring speed decoupling and strengthening interaction global autocorrelation matrix to obtain an optimized real-time temperature-stirring speed decoupling and strengthening interaction global representation vector, wherein interpolation or zero padding is performed when the eigenvalue is insufficient. Finally, the optimized real-time temperature-stirring speed decoupling and strengthening interaction global representation vector is input into the classifier-based stirring speed optimization module to obtain the optimization instruction.

[0045] That is, through the linear target mapping representation based on the similarity distance representation matrix of the real-time temperature-stirring speed decoupling enhanced interaction global representation vector, the self-correlation of the real-time temperature-stirring speed decoupling enhanced interaction global representation vector is instantiated with a secondary target mapping representation based on a multi-level distribution hierarchy, and the correlation mismatch negative impact factor is compensated by the association fusion kernel bias to improve the degree of instance determination of the eigenvalue of the real-time temperature-stirring speed decoupling enhanced interaction global representation vector under similarity constraints, that is, the significance of the eigenvalue as an instance for classification regression judgment, and improve the accuracy of the optimization instructions obtained by the stirring speed optimization module based on the classifier of the real-time temperature-stirring speed decoupling enhanced interaction global representation vector. In this way, the temporal change trend of temperature and stirring speed can be collected and monitored in real time, so as to dynamically adjust the stirring speed to adapt to the real-time needs of temperature changes and other production conditions, thereby reducing human intervention and improving the automation level of stirring speed control in the production process.

[0046] Based on the above embodiments, see Figure 3 As shown in FIG. 1 , it is a flow chart of a production management method of a special sealing primer for a wet base surface in an embodiment of the present application. Figure 3 As shown, the production management method of the special sealing primer for wet base surfaces according to the embodiment of the present application includes the steps of: S510, managing the procurement, inventory and quality inspection of raw materials; S520, formulating production plans and scheduling production resources; S530, real-time monitoring and controlling various parameters in the production process; S540, inspecting and recording product quality; S550, managing equipment maintenance.

[0047] Among them, in step S530, various parameters in the production process are monitored and controlled in real time, including: obtaining a time queue of the real-time temperature of the epoxy resin collected by the temperature sensor; obtaining a time queue of the real-time stirring speed collected by the stirring speed monitor; performing sequence segmentation on the time queue of the real-time temperature and the time queue of the real-time stirring speed based on the same time scale to obtain a sequence of local temporal input vectors of real-time temperature and a sequence of local temporal input vectors of real-time stirring speed; inputting the sequence of local temporal input vectors of real-time temperature and the sequence of local temporal input vectors of real-time stirring speed into a feature forward propagation network based on significant temporal attenuation of node energy to obtain a real-time temperature temporal propagation representation vector and a stirring speed temporal propagation representation vector; inputting the real-time temperature temporal propagation representation vector and the stirring speed temporal propagation representation vector into a feature decoupling local interaction fine-grained aggregation module to obtain a real-time temperature-stirring speed decoupling enhanced interaction global representation vector as a real-time temperature-stirring speed decoupling enhanced interaction global representation feature; based on the real-time temperature-stirring speed decoupling enhanced interaction global representation feature, obtaining an optimization instruction, the optimization instruction is used to indicate that the stirring speed value at the next time point should be increased, decreased or kept unchanged.

[0048] Here, those skilled in the art will appreciate that the specific operations of each step in the production management method of the above-mentioned wet substrate special sealing primer have been referred to above. Figure 1 to Figure 2 The description of the production management system 800 for the special sealing primer for wet substrates has been described in detail, and therefore, its repeated description will be omitted.

[0049] Figure 4 This is an application scenario diagram of the production management system of the special sealant for wet base surface according to the embodiment of the present application. Figure 4 As shown, in this application scenario, first, a time queue of the real-time temperature of the epoxy resin collected by the temperature sensor is obtained (for example, Figure 4 D1 as shown in the figure) and the time sequence of the real-time stirring speed collected by the stirring speed monitor (e.g. Figure 4 Then, the time queue of the real-time temperature and the time queue of the real-time stirring speed are input to a server (for example, Figure 4 S) as shown in , wherein the server is able to use the production management algorithm of the special sealing primer for wet base surfaces to process the time queue of the real-time temperature and the time queue of the real-time stirring speed to obtain an optimization instruction for indicating that the stirring speed value at the next time point should be increased, decreased or kept unchanged.

[0050] Based on the above embodiment, another exemplary embodiment of an electronic device is also provided in the embodiments of the present application. In some possible implementations, the electronic device in the embodiments of the present application may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of the production management method of the special sealing primer for wet base surface in the above embodiment when executing the program.

[0051] The embodiment of the present application also provides a computer-readable storage medium, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the production management method of the special sealing primer for wet base surface according to the embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc.

[0052] The embodiment of the present application also provides a computer program product or computer program, which includes computer executable instructions, and the computer executable instructions are stored in a computer readable storage medium. The processor of the computer device reads the computer executable instructions from the computer readable storage medium, and the processor executes the computer executable instructions, so that the computer device executes the production management method of the special sealing primer for wet base surface according to the embodiment of the present application.

[0053] Those skilled in the art will appreciate that the contents disclosed in this application may be subject to various variations and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0054] In addition, although the present application makes various references to certain units in the system according to embodiments of the present application, any number of different units can be used and run on the client and / or server. The units are only illustrative, and different aspects of the system and method can use different units.

[0055] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software function modules. The present application is not limited to any particular form of combination of hardware and software.

[0056] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined as such herein.

[0057] The above is an explanation of the present application and should not be considered as limiting thereof. Although several exemplary embodiments of the present application have been described, those skilled in the art will readily appreciate that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present application.

Claims

1. A production management system for a special sealant for a wet base surface, characterized in that: include: Raw materials management module, used to manage the procurement, inventory and quality inspection of raw materials; Production planning module, used to formulate production plans and dispatch production resources; Production process control module, used to monitor and control various parameters in the production process in real time; Quality control module, used to detect and record product quality; The equipment maintenance module is used to manage the maintenance and upkeep of equipment.

2. The production management system of the special sealer for wet base surface according to claim 1, characterized in that: The production process control module comprises: The epoxy resin real-time temperature acquisition unit is used to acquire the time queue of the real-time temperature of the epoxy resin acquired by the temperature sensor; A real-time stirring speed acquisition unit, used to acquire a time queue of the real-time stirring speed acquired by the stirring speed monitor; A real-time parameter time scale segmentation unit, used for performing sequence segmentation on the time queue of the real-time temperature and the time queue of the real-time stirring speed based on the same time scale to obtain a sequence of local time series input vectors of the real-time temperature and a sequence of local time series input vectors of the real-time stirring speed; A real-time parameter time series propagation unit, used for inputting the sequence of the real-time temperature local time series input vector and the sequence of the real-time stirring speed local time series input vector into a feature forward propagation network based on significant time series attenuation of node energy to obtain a real-time temperature time series propagation representation vector and a stirring speed time series propagation representation vector; A real-time temperature-stirring speed aggregation unit, used for inputting the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector into a feature decoupling local interaction fine-grained aggregation module to obtain a real-time temperature-stirring speed decoupling enhanced interaction global representation vector as a real-time temperature-stirring speed decoupling enhanced interaction global representation feature; The stirring speed value control unit is used to obtain an optimization instruction based on the real-time temperature-stirring speed decoupling enhanced interaction global representation feature, and the optimization instruction is used to indicate whether the stirring speed value at the next time point should be increased, decreased or kept unchanged.

3. The production management system of the special sealer for wet base surface according to claim 2, characterized in that: The real-time parameter timing propagation unit comprises: A real-time temperature local time series energy significant descriptor calculation subunit is used to calculate the energy significant descriptor of each real-time temperature local time series input vector in the sequence of the real-time temperature local time series input vector based on the mean and standard deviation of each real-time temperature local time series input vector to obtain a sequence of real-time temperature local time series energy significant descriptors; A timestamp extraction subunit, used for extracting the timestamp of each real-time temperature local time series input vector in the sequence of the real-time temperature local time series input vector to obtain a sequence of real-time temperature timestamps; A vector slicing subunit, used to use the real-time temperature local time series input vector corresponding to the current time point in the sequence of the real-time temperature local time series input vector as the current node feature vector and use the real-time temperature local time series input vectors corresponding to other time points as the historical node feature vectors to obtain a sequence of the current real-time temperature local time series input vector and the historical real-time temperature local time series input vector; A real-time temperature energy time decay factor calculation subunit, used to calculate the energy time decay factor of each historical real-time temperature local time series input vector in the sequence of the historical real-time temperature local time series input vector relative to the current real-time temperature local time series input vector to obtain a sequence of real-time temperature local time series energy time decay factors; A historical real-time temperature local time series propagation subunit, used to perform time series propagation aggregation on the sequence of the historical real-time temperature local time series input vectors using the sequence of the real-time temperature local time series energy significant descriptors as positive adjustment factors and the sequence of the real-time temperature local time series energy time decay factors as negative adjustment factors to obtain a historical real-time temperature local time series propagation aggregation representation feature vector; The fusion subunit is used to fuse the historical real-time temperature local time series propagation aggregation representation feature vector and the current real-time temperature local time series input vector to obtain the real-time temperature time series propagation representation vector.

4. The production management system of the special sealer for wet base surface according to claim 3, characterized in that: The real-time temperature local temporal energy significant descriptor calculation subunit is used to: Respectively calculating the mean and standard deviation of the real-time temperature local time series input vector to obtain the real-time temperature local time series feature mean and the real-time temperature local time series feature standard deviation; Calculating the position difference between the real-time temperature local time series input vector and the real-time temperature local time series feature mean to obtain a real-time temperature local time series difference vector; Calculating the fourth power of each eigenvalue in the real-time temperature local time series difference vector to obtain a real-time temperature local time series modulation difference vector; Calculating the expected value of the real-time temperature local timing modulation difference vector to obtain the real-time temperature local timing expected value; The real-time temperature local time series expected value is divided by the fourth power of the real-time temperature local time series feature standard deviation to obtain the real-time temperature local time series energy significant descriptor.

5. The production management system of the special sealer for wet base surface according to claim 4, characterized in that: The real-time temperature energy time attenuation factor calculation subunit is used to: The real-time temperature timestamp corresponding to the current real-time temperature local time series input vector is subtracted from the real-time temperature timestamp corresponding to each historical real-time temperature local time series input vector, and then rounded down to obtain a sequence of historical real-time temperature time span values; After calculating the square of the positional division of the sequence of historical real-time temperature time span values ​​and the time attenuation inverse scaling parameter to obtain a sequence of historical real-time temperature time span square modulation values, the sequence of historical real-time temperature time span square modulation values ​​is positionally multiplied by the attenuation rate positive scaling parameter to obtain a sequence of real-time temperature time series span energy attenuation coefficients; Taking each real-time temperature time series span energy attenuation coefficient in the sequence of the real-time temperature time series span energy attenuation coefficient as an exponential power, a natural exponential function value with a natural constant e as a base is calculated to obtain a sequence of the real-time temperature local time series energy time attenuation factors.

6. The production management system of the special sealer for wet base surface according to claim 5, characterized in that: The historical real-time temperature local time series propagation subunit is used to: divide the sequence of the real-time temperature local time series energy significant descriptors by the sequence of the real-time temperature local time series energy time attenuation factors by position to obtain a sequence of real-time temperature adjustment factors, and calculate the position-weighted sum of the sequence of the real-time temperature adjustment factors and the sequence of the historical real-time temperature local time series input vectors to obtain the historical real-time temperature local time series propagation aggregation representation feature vector.

7. The production management system of the special sealer for wet base surface according to claim 6, characterized in that: The real-time temperature-stirring speed polymerization unit comprises: A feature decoupling subunit, used for feature decoupling the real-time temperature time series propagation representation vector and the stirring speed time series propagation representation vector to obtain a sequence of real-time temperature local time series propagation aggregation representation vectors and a sequence of stirring speed local time series propagation aggregation representation vectors; A real-time temperature-stirring speed local temporal sequence semantic association interaction subunit is used to calculate the local semantic association interaction vector between each corresponding group of real-time temperature local temporal sequence propagation aggregation representation vectors and stirring speed local temporal sequence propagation aggregation representation vectors in the sequence of real-time temperature local temporal sequence propagation aggregation representation vectors and the sequence of stirring speed local temporal sequence propagation aggregation representation vectors to obtain a sequence of real-time temperature-stirring speed local temporal sequence semantic association interaction vectors; A real-time temperature-stirring speed local temporal sequence fine-grained attention weight calculation subunit, used to calculate the fine-grained attention weight of each real-time temperature-stirring speed local temporal sequence semantic association interaction vector in the sequence of real-time temperature-stirring speed local temporal sequence semantic association interaction vectors to obtain a sequence of real-time temperature-stirring speed local temporal sequence fine-grained attention weights; A deactivation processing subunit, used for inputting the sequence of real-time temperature-stirring speed local time series fine-grained attention weights into a random deactivation module to obtain a sequence of real-time temperature-stirring speed local time series fine-grained attention weights after deactivation processing; A weighted sum calculation subunit, used to calculate the weighted sum of the sequence of real-time temperature-stirring speed local temporal fine-grained attention weights after the deactivation process as the weight distribution, to obtain the real-time temperature-stirring speed decoupling reinforcement interaction global representation vector; Wherein, the real-time temperature-stirring speed local time series fine-grained attention weight calculation subunit is used to: After multiplying each real-time temperature-stirring speed local time-series semantic association interaction vector in the sequence of real-time temperature-stirring speed local time-series semantic association interaction vectors by a weight matrix, the obtained vector is added to the bias vector by position to obtain a sequence of real-time temperature-stirring speed local time-series semantic association interaction modulation vectors; Inputting the sequence of real-time temperature-stirring speed local temporal semantic association interaction modulation vectors into a tanh function for activation processing to obtain a sequence of real-time temperature-stirring speed local temporal semantic association interaction activation vectors; Each real-time temperature-stirring speed local temporal sequence semantic association interaction activation vector in the sequence of the real-time temperature-stirring speed local temporal sequence semantic association interaction activation vector is multiplied by a weight coefficient vector to obtain a sequence of the real-time temperature-stirring speed local temporal sequence fine-grained attention weights.

8. The production management system of the special sealer for wet base surface according to claim 7, characterized in that: The real-time temperature-stirring speed local temporal semantic association interaction subunit includes: Respectively calculating the position difference, position dot product and position addition between the real-time temperature local time series propagation aggregation representation vector and the stirring speed local time series propagation aggregation representation vector to obtain the real-time temperature-stirring speed local time series propagation aggregation difference vector, the real-time temperature-stirring speed local time series propagation aggregation dot product vector and the real-time temperature-stirring speed local time series propagation aggregation addition vector; The real-time temperature-stirring speed local time series propagation aggregate difference vector, the real-time temperature-stirring speed local time series propagation aggregate dot product vector and the real-time temperature-stirring speed local time series propagation aggregate sum vector are cascaded and then one-dimensional convolutional coding is performed to obtain a real-time temperature-stirring speed local time series multi-dimensional fusion vector; The real-time temperature-stirring speed local time series multi-dimensional fusion vector is subjected to a local window-based maximum pooling process to obtain the real-time temperature-stirring speed local time series semantic association interaction vector.

9. The production management system of the special sealer for wet base surface according to claim 8, characterized in that: The stirring speed value control unit is used to: input the real-time temperature-stirring speed decoupling reinforcement interaction global representation vector into a classifier-based stirring speed optimization module to obtain the optimization instruction, and the optimization instruction is used to indicate that the stirring speed value at the next time point should increase, decrease or remain unchanged.

10. A production management method for a special sealing primer for a wet base surface, characterized in that: include: Manage the procurement, inventory and quality testing of raw materials; Formulate production plans and dispatch production resources; Real-time monitoring and control of various parameters in the production process; Test and record product quality; Manage the care and maintenance of equipment.

Images