Gas equipment warehouse management method and device based on industrial internet of things, medium and equipment

Abstract

The invention discloses a gas equipment warehouse management method and device based on the industrial Internet of Things, a medium and equipment. The method comprises the steps that equipment information and warehouse environment information of gas equipment to be stored are collected; preprocessing the equipment information of the to-be-stored gas equipment and the environment information; a gas equipment storage management model is constructed and trained; and analyzing the preprocessed equipment information and environment information of the to-be-stored gas equipment based on the trained gas equipment storage management model so as to output probability distribution of storage positions of the to-be-stored gas equipment in a warehouse. Scientific storage of the gas equipment can be achieved, and the risk that the gas equipment is damaged or fails due to improper storage is reduced.

Description

Technical Field

[0001] The present application belongs to the technical field of warehousing and logistics management, and specifically relates to a method, device, medium and equipment for warehousing management of gas equipment based on industrial Internet of Things. Background Art

[0002] Existing gas equipment management methods mainly rely on manual experience for equipment storage and maintenance, lacking systematic data support and intelligent decision-making methods, which can easily lead to problems such as improper storage or untimely maintenance of gas equipment, thereby affecting the service life and safety of gas equipment. In addition, traditional management methods are difficult to achieve real-time monitoring and dynamic adjustment, and cannot effectively respond to changes in warehouse environment and equipment status updates, reducing the overall efficiency and accuracy of gas equipment storage management. Summary of the invention

[0003] The main purpose of this application is to provide a gas equipment storage management method, device, medium and equipment based on industrial Internet of Things. This application can scientifically store various types of gas equipment, thereby extending the service life of various types of gas equipment.

[0004] To achieve the above objectives, this application provides the following technical solutions:

[0005] A gas equipment storage management method based on industrial Internet of Things, the method comprising: collecting equipment information and storage environment information of gas equipment to be stored; preprocessing the equipment information and environment information of the gas equipment to be stored; building a gas equipment storage management model and training it; and analyzing the preprocessed equipment information and environment information of the gas equipment to be stored based on the trained gas equipment storage management model to output the probability distribution of the storage location of the gas equipment to be stored in the warehouse.

[0006] Optionally, the device information and environmental information of the gas equipment to be stored are preprocessed, including: cleaning the device information and environmental information; converting the format of the cleaned device information and environmental information; and standardizing the device information and environmental information after the format conversion.

[0007] Optionally, the gas equipment storage management model includes: a first feature extraction network, used to extract features from the information of the gas equipment to be stored to obtain a first feature; a second feature extraction network, used to extract features from the storage environment information to obtain a second feature; a feature fusion network, used to fuse the first feature and the second feature to obtain a fused feature; and an output network, used to output the probability distribution of the storage location of the gas equipment to be stored in the warehouse based on the fused feature.

[0008] Optionally, the first feature extraction network includes: an input layer, an embedding layer, a position encoding, a self-attention mechanism, a multi-head attention, a memory unit, a context-aware module, a convolutional layer and an adaptive pooling layer connected in sequence.

[0009] Optionally, the second feature extraction network includes: an input layer, a first LSTM layer, a second LSTM layer, a fully connected layer and an output layer connected in sequence.

[0010] Optionally, the feature fusion network includes: a feature fusion layer, a first fully connected layer, a second fully connected layer, and an activation function connected in sequence.

[0011] Optionally, the gas equipment storage management model is trained through the following steps: collecting equipment information of different gas equipment and various environmental information in the warehouse to obtain an information data set, and dividing the data set into a training set and a verification set; setting training parameters, and using the training set to train the gas equipment storage management model until the maximum number of training times is reached; using the verification set to verify the trained gas equipment storage management model, and using it as a model performance evaluation indicator. When each indicator meets the preset value, the model verification passes; otherwise, resetting the training parameters or expanding the training samples in the training set until the model verification passes.

[0012] In addition, the present application also provides a warehouse logistics management device based on the industrial Internet of Things, which includes: a collection module for collecting equipment information and storage environment information of the gas equipment to be stored; a preprocessing module for preprocessing the equipment information and environment information of the gas equipment to be stored; a model construction and training module for constructing a gas equipment storage management model and training it; an output module for analyzing the preprocessed equipment information and environment information of the gas equipment to be stored based on the trained gas equipment storage management model to output the probability distribution of the storage location of the gas equipment to be stored in the warehouse.

[0013] In addition, the present application also provides a storage medium, which includes instructions, and when the instructions are executed on a computer, the computer executes the method as described in any of the preceding items.

[0014] In addition, the present application also provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any of the preceding items when executing the program.

[0015] Compared with the existing technology, the present application can bring the following technical effects: the present application uses deep learning technology to extract and fuse the features of gas equipment information and storage environment information respectively, thereby outputting the probability distribution of the storage location of the gas equipment in the warehouse. The present application can allocate storage space scientifically and reasonably based on the characteristics of the gas equipment (such as material, size, shelf life, etc.) and changes in the storage environment (such as temperature, humidity, etc.), ensuring that various types of gas equipment can obtain the best storage conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of a gas equipment storage management method based on industrial Internet of Things provided by another embodiment of the present application;

[0017] Figure 2 is a structural diagram of a gas equipment storage management model provided by another embodiment of the present application;

[0018] Figure 3 is a structural diagram of a first feature extraction network provided by another embodiment of the present application;

[0019] Figure 4 yes Figure 3 A schematic diagram of the structure of a context-aware module in the first feature extraction network shown;

[0020] Figure 5 yes Figure 3 A schematic diagram of the structure of a convolutional network in the first feature extraction network shown;

[0021] Figure 6 is a schematic diagram of the structure of a second feature extraction network provided in another embodiment of the present application;

[0022] Figure 7 is a structural diagram of a feature fusion network provided by another embodiment of the present application;

[0023] Figure 8 This is a structural schematic diagram of a gas equipment storage management device based on industrial Internet of Things provided by an embodiment of the present application;

[0024] Fig. 9 A schematic diagram of the structure of a storage medium provided by another embodiment of the present application;

[0025] Fig.10 It is a structural schematic diagram of an electronic device provided in another embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0028] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0029] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0030] Figure 1 The flowchart of the gas equipment storage management method based on the industrial Internet of Things according to one embodiment of the present application is shown in FIG. 1 , wherein the method is executed by an electronic device, and the electronic device includes a computer with computing power, a server, etc. Figure 1 As shown, the method includes:

[0031] S100: Collecting equipment information and storage environment information of the gas equipment to be stored;

[0032] In this step, the gas equipment includes, for example, gas appliances (such as gas stoves, water heaters, wall-mounted boilers, etc.), gas accessories (such as burners, controllers, valves, pipelines, sensors, etc.), safety equipment (such as alarms, shut-off valves, etc.), fuel containers (such as tanks, gas cylinders, etc.), packaging materials (such as packaging boxes, foam, plastic films, etc.), and product-attached documents (such as operating manuals, warranty cards, installation guides, etc.). The equipment information of the gas equipment to be stored includes at least the equipment name, production and storage date, specifications and models, dimensions and weight, storage conditions (such as temperature, humidity, etc.), shelf life or validity period; the environmental information includes at least the temperature, humidity, lighting, air quality, and pressure conditions of each storage area in the warehouse.

[0033] S200: Preprocessing the device information and environment information of the gas device to be stored;

[0034] S300: Build and train a gas equipment storage management model;

[0035] S400: Analyze the pre-processed equipment information and environmental information of the gas equipment to be stored based on the trained gas equipment storage management model to output the probability distribution of the storage location of the gas equipment to be stored in the warehouse.

[0036] In this embodiment, different types of gas equipment have different requirements for storage conditions. For example, metal equipment is prone to rust or corrosion in a high humidity environment, which affects its service life; plastic parts or other non-metallic equipment are prone to accelerated aging in a high temperature environment and become brittle or deformed, posing certain safety hazards. Therefore, in order to ensure the safety and functionality of different types of gas equipment during subsequent use, it is necessary to scientifically store different types of gas equipment based on the environmental conditions of each area in the warehouse. This application can ensure the safety and functionality of various types of gas equipment during subsequent use, extend the service life of gas equipment, and reduce the risk of damage or failure of gas equipment due to improper storage by effectively integrating and analyzing gas equipment information and environmental information.

[0037] In another exemplary embodiment, in step S200, the device information and environment information of the gas device to be stored are preprocessed, including:

[0038] S201: Cleaning the equipment information and environment information of the gas equipment to be stored;

[0039] In this step, data cleaning includes removing duplicate records, handling missing values ​​(by deleting records with missing values ​​or filling missing values ​​with the mean, median, or mode), and identifying and correcting errors (finding and correcting erroneous data entries, such as outliers or inconsistent data).

[0040] S202: Format conversion of the cleaned equipment information and environmental information, specifically including: converting all date and time fields into a unified format, such as ISO 8601 (YYYY-MM-DDHH:MM:SS), which helps to perform consistent timestamp processing in time series analysis; converting all numeric data into numeric formats (such as integers or floating point numbers) rather than strings or other forms, to avoid analysis errors or model training failures due to data type mismatch; converting non-numeric categorical data (such as equipment category, supplier name, etc.) into numeric data using one-hot encoding or label encoding, so that the gas equipment storage management model can understand and process these data.

[0041] S203: Standardize the device information and environment information after format conversion.

[0042] In this step, the device information and the environment information after format conversion may be converted to the same scale by using minimum-maximum normalization or Z-score standardization to eliminate the influence of the dimension, so that data of different attributes can be directly compared.

[0043] In another exemplary embodiment, Figure 2 As shown, the gas equipment storage management model includes: a first feature extraction network, used to extract features from the equipment information of the gas equipment to be stored to obtain a first feature; a second feature extraction network, used to extract features from the environmental information in the warehouse to obtain a second feature; a feature fusion network, used to fuse the first feature and the second feature to obtain a fused feature; and an output network, used to output the probability distribution of the storage location of the gas equipment to be stored in the warehouse based on the fused feature.

[0044] Specifically, Figure 3 As shown, the first feature extraction network includes an input layer, an embedding layer, a self-attention mechanism, a multi-head attention mechanism, a long short-term memory network, a context perception module, a convolutional network and an adaptive pooling layer connected in sequence, and the first feature extraction network also includes a position code, and the position code is connected to the output end of the embedding layer.

[0045] In the first feature extraction network, the input layer is used to receive equipment information of the gas equipment to be stored, and the equipment information includes but is not limited to multiple categories such as text descriptions about the gas equipment, gas equipment images, and sensor data.

[0046] The embedding layer is used to convert the device information of the gas equipment to be stored input by the input layer into a dense vector representation. Specifically, the working mechanism of the embedding layer is as follows: First, a dictionary is created. For each category in the device information (such as device model, supplier name, etc.), a unique identifier or index is required, and these identifiers constitute a dictionary. Secondly, the index is mapped to map each device information to the corresponding index in this dictionary, which means that each category item will be replaced by its index number in the dictionary. Thirdly, matrix embedding is performed. The embedding layer contains an embedding matrix, each row of which corresponds to an index in the dictionary, and each row is a vector of fixed length (i.e., a dense vector). This matrix is ​​usually randomly initialized and is continuously updated during the model training process to find the vector that can best represent the characteristics of the device information. Finally, a vectorized representation is performed. When the device information passes through the embedding layer, each index number will be replaced by the corresponding row vector in the embedding matrix. In this way, the original category data is converted into a numerical vector form. Through the transformation of the embedding layer, the original text information (such as the name, specification model, etc. of the device) or category information (such as the device category, supplier name, etc.) is mapped to a high-dimensional space. Each device information is represented as a dense vector, which can carry rich information and capture the similarities and differences between different device information.

[0047] The position encoding is used to add position information to the dense vector representation output by the embedding layer to ensure that the equipment information of the gas equipment after conversion by the embedding layer can not only carry the characteristics of the gas equipment itself (including model, specifications, etc.), but also carry the positional relationship of this information in the input data.

[0048] The self-attention mechanism adopts a deformable self-attention mechanism, which allows the gas equipment storage management model to dynamically adjust its focus by introducing a learnable position offset parameter, so as to more effectively capture the key features in the input data. Specifically, the deformable self-attention mechanism includes a position offset prediction layer, an attention weight calculation layer of the offset position, a softmax activation function, and a weighted summation layer connected in sequence, wherein the position offset prediction layer is responsible for predicting the position offset, which can be achieved by a group of convolutional layers or fully connected layers, and its purpose is to generate a set of offset vectors, which will be used to adjust the position of the query in the attention mechanism. For example, when processing gas equipment information, this layer can predict which specific position information is more important for the optimal storage location of a certain type of equipment; the attention weight calculation of the offset position is used to add the position offset to the query of the self-attention mechanism, so that the query can point to a more flexible position. When processing gas equipment data, the gas equipment storage management model can adjust its attention to different position information according to actual needs, such as the status of certain key components or specific area conditions in the warehouse. The softmax activation function uses a standard attention score calculation method (such as dot product attention) to calculate the attention weight of each query relative to all keys. The softmax function can ensure that the sum of these weights is 1 and highlight the most important information, which helps to highlight the features that are most important for determining the placement of the equipment. The weighted summation performs a weighted summation of the values ​​according to the obtained attention weights to obtain the final attention output, so that the model can comprehensively consider various factors, such as the specific specifications of the gas equipment, the ambient temperature and humidity, etc., to generate decision recommendations on the optimal placement of the gas equipment.

[0049] The multi-head attention mechanism includes multiple parallel attention heads, each of which focuses on different feature subspaces of the input data (for gas appliances, these features include equipment type (such as gas stoves, water heaters, etc.), specifications and models, size and weight, shelf life or validity period, and environmental information such as temperature and humidity in the warehouse) and processes the input data independently to extract key information from different perspectives. For example, one attention head focuses on analyzing the similarities and differences between different gas appliances, such as the commonalities and differences between gas stoves and water heaters; another attention head focuses on identifying key environmental factors that affect storage conditions, such as how changes in temperature or humidity affect the storage of gas appliances. Finally, the output results of all attention heads are merged to form a comprehensive representation, so that the gas appliance storage management model can take into account multiple factors at the same time. For example, the optimal storage location of a specific gas appliance depends not only on its physical properties, but also on its required storage conditions. By combining information from each attention head, the gas appliance storage management model can generate a more comprehensive and accurate decision basis.

[0050] The LSTM network can analyze time series data through its special gating mechanism (input gate, forget gate and output gate). Time series data includes, for example, changes in the storage environment and historical maintenance records of gas equipment. The LSTM network can further capture the long-term dependencies in these time series data, thereby adapting to the ever-changing storage environment. Based on the LSTM network, not only can the gas equipment storage management model's ability to understand time series information be enhanced, but also the quality of feature extraction can be improved, helping the gas equipment storage management model to comprehensively consider historical data, current status and future trends, so as to optimize the best storage location decision for gas equipment and ensure the safety of gas equipment and the efficiency of warehouse management.

[0051] The context-aware module is implemented through a gating mechanism or an attention mechanism to ensure that the processing of each device information can take into account the global context. Figure 4As shown, the context-aware module includes an input layer, a global pooling layer, an attention mechanism layer, a gating mechanism layer, a feature fusion layer and an output layer. Specifically, the input layer is used to receive the original gas equipment information, which includes the name, specification, model, size and weight of the gas equipment, as well as environmental data such as temperature and humidity in the warehouse. The global pooling layer is used to capture the global features of the entire input sequence. For gas equipment, the global pooling layer can extract the macro features common to all gas equipment, such as the overall storage demand trend or the influence of general environmental conditions. The attention mechanism layer is used to identify the relationship between the elements in the input sequence and highlight those parts that are most important to the current decision. For example, when determining the best storage location for a particular gas equipment, the attention mechanism can help the gas equipment storage management model focus on the key attributes of the particular gas equipment and its correlation with other surrounding gas equipment or environmental factors. The gating mechanism layer uses the gating mechanism in the gated recurrent unit (GRU) or the long short-term memory network (LSTM) to control the information flow, so that the gas equipment storage management model can selectively remember or forget certain details when processing gas equipment information, so as to better maintain long-term dependencies. For example, if a certain type of gas equipment has frequently encountered specific problems in the past period of time, the gating mechanism can help the gas equipment storage management model remember this and adjust the subsequent storage strategy accordingly. The feature fusion layer is used to combine the features extracted from different levels to form a comprehensive representation. For gas equipment, through the feature fusion layer, the specific attributes of a single gas equipment can be combined with the overall status of the warehouse where it is located to generate a comprehensive understanding. The output layer can provide the final result based on the above comprehensive representation, that is, to provide the optimal storage solution for gas equipment.

[0052] In summary, the context-aware module can ensure that the processing of each device information can take into account the global context, and selectively retain important information and ignore insignificant parts through a gating mechanism or an attention mechanism. In this way, the gas equipment storage management model can more accurately identify the most valuable information for the current decision, so as to make more reasonable decisions. For example, when determining the best storage location for a specific gas equipment, the gas equipment storage management model can focus more on the key attributes of the equipment and its relationship with the surrounding environment, while ignoring information that does not directly affect the storage decision (for example, including non-critical equipment attributes, such as the color of the equipment, production date, etc.).

[0053] like Figure 5As shown, the convolutional network includes a 3×3 convolutional layer, a maximum pooling layer, a 3×3 convolutional layer, a maximum pooling layer, and a 3×3 convolutional layer connected in sequence. In this network, the 3×3 convolutional layer can capture local patterns or features in the input data (such as gas equipment images, sensor data, etc.). For gas equipment, these features include subtle differences in the appearance of the equipment, label information, or changes in environmental monitoring sensor readings. The convolution operation scans the input data by applying a series of small filters (kernels), each of which is responsible for detecting a specific type of pattern or feature. The maximum pooling layer reduces the data dimension by selecting the maximum value of each local area while maintaining the main features, which helps the gas equipment storage management model to have a certain invariance to changes in position and scale, that is, even if the position of the gas equipment moves slightly or the size is slightly different, the gas equipment storage management model can still identify its key features. By stacking multiple convolutional layers and pooling layers, the convolutional network can construct a feature hierarchy from low-level to high-level. This hierarchical structure enables the gas equipment storage management model to gradually learn from simple edges and textures to more complex structures and patterns, such as different types of gas equipment and their specific components, thereby providing the gas equipment storage management model with rich information and helping it make more accurate decisions.

[0054] like Figure 6 As shown, the second feature extraction network includes an input layer, a first LSTM layer, a second LSTM layer, a fully connected layer and an output layer connected in sequence, wherein the second feature extraction network adopts a residual connection, that is, the input of the input layer and the input of the first LSTM layer are added as the output of the second LSTM layer.

[0055] Specifically, the input layer is used to receive storage environment information, including temperature, humidity, light intensity, etc.

[0056] The first LSTM layer uses a gating mechanism (input gate, forget gate, and output gate) to preliminarily process the storage environment information to capture the long-term dependencies in the storage environment information, such as:

[0057] Identify temperature trends: If the temperature in the warehouse continues to rise over the past few days, the first LSTM layer can identify this trend and save it as a feature.

[0058] Humidity fluctuations: For humidity changes, if there are regular fluctuations (such as higher humidity in the morning and evening and lower humidity in the afternoon), the first LSTM layer can also capture this pattern.

[0059] The second LSTM layer is used to further refine features and continue to capture potential time dependencies in storage environment information. For example, based on the temperature trend, the second LSTM layer will find that there is a certain correlation between increased temperature and decreased humidity, which may be particularly critical for the storage of certain types of gas equipment. The second LSTM layer can also build more abstract and complex feature representations to help reveal the specific impact of storage environment information on different types of gas equipment. For example, if a certain type of gas equipment is found to be more prone to problems in a high humidity environment, the second LSTM layer can capture this feature.

[0060] The second LSTM layer can not only process real-time data, but also learn from historical data to construct more abstract and complex feature representations, which helps to reveal the specific impact of storage environment information on different types of gas equipment.

[0061] In addition, the second feature extraction network also adopts a residual connection mechanism. Based on the residual connection, it can alleviate the gradient vanishing problem that may occur in the deep network, and it also helps the original environmental information to be directly transmitted to the deeper network layer, so that the gas equipment storage management model can learn a richer hierarchical representation. The fully connected layer is used to map the features extracted by all previous layers into a vector space of a fixed size, so that the gas equipment storage management model can better understand and interpret the storage environment information. The output layer is used to provide a comprehensive feature representation of the storage environment information (i.e., the second feature), which, together with the first feature, supports the gas equipment storage management model to make decisions about the optimal placement of gas equipment.

[0062] In summary, the second feature extraction network can effectively extract useful features from the warehouse environment information, especially those patterns and trends related to time series, thus providing an important basis for the decision-making of the entire warehouse logistics management system.

[0063] like Figure 7 As shown, the feature fusion network includes: a feature fusion layer, a first fully connected layer, a second fully connected layer, a third fully connected layer and an activation function, wherein the number of nodes in each of the first fully connected layer, the second fully connected layer and the third fully connected layer can be adjusted according to the complexity of the feature. For example, the first fully connected layer can have more nodes to capture more features, and the subsequent fully connected layers can gradually reduce the number of nodes to extract more abstract features.

[0064] The feature fusion layer is responsible for fusing the features from the first feature extraction network and the second feature extraction network. The feature fusion layer can specifically use a gate mechanism to control which features are retained and which are suppressed to ensure that only the most relevant information is used to generate the final feature representation.

[0065] The gating mechanism specifically includes:

[0066] The input gate is used to determine which information will be written into the cell state to control which input features will be stored. The input gate is specifically represented as:

[0067] i t =σ(W i ·[h t-1 ,x t ]+b i )

[0068] Among them, W i represents the weight matrix of the input gate, b i represents the bias term of the input gate, x t represents the input of the current time step, h t-1 represents the hidden state of the previous time step, and σ represents the sigmoid function.

[0069] The Forget Gate is used to determine which information will be removed from the cell state to reduce the interference of redundant information on model decision making. The Forget Gate is specifically expressed as:

[0070] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0071] Among them, W f represents the weight matrix of the forget gate, b f Represents the bias term of the forget gate.

[0072] The output gate is used to determine which part of the unit state will be passed as output to the next time step to ensure that only critical information is passed to the next processing stage. The output gate is specifically expressed as:

[0073] o t =σ(W o ·[h t-1 ,x t ]+b o )

[0074] Among them, W o represents the weight matrix of the output gate, b o Represents the bias term of the output gate.

[0075] In addition, the gating mechanism also includes a candidate state, a cell state, and a current hidden state, wherein:

[0076] The candidate status It is expressed as:

[0077]

[0078] Among them, W c represents the weight matrix of the candidate state, b c A bias term representing the candidate state.

[0079] The cell state c t It is expressed as:

[0080]

[0081] Among them, c t-1 is the cell state at the previous time step.

[0082] The current hidden state h t It is expressed as:

[0083] h t =o t ·tanh(c t )

[0084] Among them, h t Indicates the current hidden state.

[0085] The first fully connected layer has a large number of nodes to capture as many feature combinations as possible. This layer can handle complex nonlinear relationships and learn subtle patterns in the data through a large number of nodes. The number of nodes in the second fully connected layer is reduced compared to the first fully connected layer, and can be used to gradually extract more abstract and high-level features. By reducing the number of nodes, the second fully connected layer enables the gas equipment storage management model to begin to compress and simplify the features, thereby extracting a more refined feature representation. The third fully connected layer further reduces the number of nodes, which helps the gas equipment storage management model focus on the most critical information. In summary, the first fully connected layer, the second fully connected layer and the third fully connected layer are superimposed, and the number of nodes in each layer is gradually reduced, so that the gas equipment storage management model can gradually abstract and refine features from the input data to enhance the expression and generalization capabilities of the gas equipment storage management model, so as to make more accurate decisions on the optimal placement of gas equipment.

[0086] In another exemplary embodiment, in step S300, the gas equipment storage management model is trained by the following steps:

[0087] S301: Collect equipment information of different gas equipment and various environmental information in the warehouse to obtain an information data set, and divide the information data set into a training set and a verification set;

[0088] S302: Setting training parameters, for example, the training batch size is 32, the number of training rounds is 100, the learning rate is 0.001, and the gas equipment storage management model is trained using the training set until the maximum number of training times is reached;

[0089] S303: Use the validation set to validate the gas equipment storage management model, and use accuracy, recall and F1 score as evaluation indicators to evaluate the model performance. When each indicator reaches 0.9 or above, the model verification is passed; otherwise, adjust the training parameters (for example, adjust the number of training rounds to 200, adjust the learning rate to 0.05) or expand the training samples to retrain the model until the model verification is passed.

[0090] Below, the present application provides an illustrative description of the method described in the present application based on several specific gas equipment and specific environmental information.

[0091] It is now necessary to store household gas stoves, plastic gas accessories (such as plastic pipes) and gas control valves, among which,

[0092] The shelf life of household gas stoves is 2 years, and the storage conditions are: temperature below 30℃ and relative humidity not exceeding 70%.

[0093] The shelf life of plastic gas accessories is 5 years. The storage conditions are: temperature between -10-40℃, avoid direct sunlight.

[0094] The gas control valve needs to be checked regularly. The storage conditions are: the temperature is not higher than 45℃ and avoid direct sunlight.

[0095] The warehouse consists of four areas: A, B, C, and D. The environmental information collected in each area is as follows:

[0096] Area A:

[0097] Temperature: 20℃ to 25℃

[0098] Humidity: 50% to 60%

[0099] Light intensity: low (with shading measures)

[0100] Air quality: Good

[0101] Ventilation: Good

[0102] Ground load bearing capacity: High

[0103] Zone B:

[0104] Temperature: 25℃ to 30℃

[0105] Humidity: 60% to 70%

[0106] Light intensity: medium Air quality: good

[0107] Ventilation: Good

[0108] Ground load-bearing capacity: Medium

[0109] Zone C:

[0110] Temperature: 30℃ to 35℃

[0111] Humidity: 70% to 80%

[0112] Light intensity: High (direct sunlight)

[0113] Air quality: Average

[0114] Ventilation condition: General

[0115] Ground load-bearing capacity: Medium

[0116] Zone D:

[0117] Temperature: 20℃ to 25℃

[0118] Humidity: 50% to 60%

[0119] Light intensity: low (with shading measures)

[0120] Air quality: Good

[0121] Ventilation: Good

[0122] Ground load bearing capacity: High

[0123] Based on manual experience and warehouse layout, the following storage methods will be adopted:

[0124] Household gas stove: placed in area B.

[0125] Plastic gas accessories: placed in Area C.

[0126] Gas control valve: placed in area A.

[0127] However, the above storage method does not fully consider the storage conditions of various gas equipment. For example, household gas stoves are suitable for storage in areas with a temperature below 30°C and a humidity not exceeding 70%, while the humidity in Area B reaches 70%, which does not fully meet the requirements. Plastic gas accessories need to be kept away from direct sunlight, while Area C has high light intensity and does not meet the storage conditions.

[0128] The above gas equipment information and environmental information are pre-processed and input into the gas equipment storage management model, and finally the following results are output:

[0129] Household gas stoves:

[0130] Zone A: 50%

[0131] Zone D: 50%

[0132] Reason: Household gas stoves need to be stored in an environment with a temperature below 30°C, humidity not exceeding 70%, and low light intensity. Both Area A and Area D meet the conditions, so the probability is equal.

[0133] Plastic gas fittings:

[0134] Zone A: 50%

[0135] Zone D: 50%

[0136] Reason: Plastic gas fittings are sensitive to temperature and light, so they should also be stored in a place with a temperature below 30°C, humidity not exceeding 70%, and low light intensity. Areas A and D also meet the conditions, so the probability is equal.

[0137] Gas control valve:

[0138] Zone A: 60%

[0139] Zone B: 40%

[0140] Reason: Gas control valves are sensitive to high temperatures and need to be stored in a place with moderate temperature and good ventilation. Both Area A and Area B meet the conditions, but since the temperature in Area A is lower than that in Area B, it is more conducive to extending the service life of the gas control, so the probability of Area A is higher.

[0141] Based on the above comparison, it can be found that the present application can scientifically and reasonably allocate storage space to ensure that various types of gas equipment obtain the best storage conditions, thereby increasing the service life of each gas equipment.

[0142] In another embodiment, if Figure 8 As shown, the present application also provides a gas equipment storage management device based on industrial Internet of Things, the device comprising: a collection module 100, used to collect equipment information and storage environment information of the gas equipment to be stored; a preprocessing module 200, used to preprocess the equipment information and environment information of the gas equipment to be stored; a model building and training module 300, used to build a gas equipment storage management model and perform training; an output module 400, used to analyze the preprocessed equipment information and environment information of the gas equipment to be stored based on the trained gas equipment storage management model, so as to output the probability distribution of the storage location of the gas equipment to be stored in the warehouse.

[0143] Based on the above embodiments, Fig. 9 , for an explanation of the computer-readable storage medium of the exemplary embodiment of the present application, please refer to Fig. 9 , the computer-readable storage medium shown is a CD 40, on which a computer program (i.e., a program product) is stored. When the computer program is executed by the processor, it will implement the various steps recorded in the above method implementation, for example, collecting equipment information and storage environment information of the gas equipment to be stored; preprocessing the equipment information and environment information of the gas equipment to be stored; building a gas equipment storage management model and training it; analyzing the preprocessed equipment information and environment information of the gas equipment to be stored based on the trained gas equipment storage management model to output the probability distribution of the storage location of the gas equipment to be stored in the warehouse.

[0144] The specific implementation methods of each step are not repeated here. It should be noted that the computer-readable storage medium includes but is not limited to phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not described one by one here.

[0145] Based on the above embodiments, the present application also provides an electronic device, as shown below: Fig.10 An electronic device for downloading a file according to an exemplary embodiment of the present application is described.

[0146] Fig.10 A block diagram of an exemplary electronic device 50 suitable for implementing the embodiments of the present application is shown, and the electronic device 50 may be a computer system or a cloud server. Fig.10 The electronic device 50 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0147] like Fig.10 As shown, the electronic device 50 includes but is not limited to: one or more processors or processing units 501, a system memory 502, and a bus 503 connecting different system components (including the system memory 502 and the processing unit 501).

[0148] The electronic device 50 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 50, including volatile and non-volatile media, removable and non-removable media.

[0149] The system memory 502 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 5021 and / or cache memory 5022. The electronic device 50 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the ROM 5023 may be used to read and write non-removable, non-volatile magnetic media ( Fig.10 is not shown in the Fig.10 As shown in FIG. 5 , a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) can be provided. In these cases, each drive can be connected to bus 503 via one or more data medium interfaces. System memory 502 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of each embodiment of the present application.

[0150] A program / utility 5025 having a set (at least one) of program modules 5024 may be stored, for example, in system memory 502, and such program modules 5024 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 5024 generally perform the functions and / or methods of the embodiments described herein.

[0151] The electronic device 50 may also communicate with one or more external devices 504 (e.g., a keyboard, a pointing device, a display, etc.). Such communication may be performed via an input / output (I / O) interface 505. Furthermore, the electronic device 50 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 506. Fig.10 As shown, the network adapter 506 communicates with other modules (such as the processing unit 501, etc.) of the electronic device 50 via the bus 503. It should be understood that although Fig.10 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 50 .

[0152] The processing unit 501 executes various functional applications and data processing by running the program stored in the system memory 502, for example, collecting the equipment information and storage environment information of the gas equipment to be stored; preprocessing the equipment information and environment information of the gas equipment to be stored; building a gas equipment storage management model and training it; analyzing the preprocessed equipment information and environment information of the gas equipment to be stored based on the trained gas equipment storage management model to output the probability distribution of the storage location of the gas equipment to be stored in the warehouse. The specific implementation of each step is not repeated here. It should be noted that although several units / modules or sub-units / sub-modules of the file concurrent downloading device are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to the embodiment of the present application, the features and functions of two or more units / modules described above can be concretized in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be concretized.

[0153] In the description of the present application, it should be noted that the terms "first", "second" and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0154] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0155] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0156] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0157] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0158] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that can be executed by a processor. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a cloud server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0159] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A gas equipment storage management method based on industrial Internet of Things, characterized in that: The method comprises: Collect equipment information and storage environment information of the gas equipment to be stored; Preprocessing the equipment information and environment information of the gas equipment to be stored; Build and train a gas equipment storage management model; The preprocessed equipment information and environmental information of the gas equipment to be stored are analyzed based on the trained gas equipment storage management model to output the probability distribution of the storage location of the gas equipment to be stored in the warehouse.

2. The warehouse logistics management method according to claim 1, characterized in that: Preprocessing the equipment information and environment information of the gas equipment to be stored includes: Cleaning the device information and environment information; Converting the format of the cleaned device information and environment information; The device information and environment information after format conversion are standardized.

3. The warehouse logistics management method according to claim 1, characterized in that: The gas equipment storage management model includes: A first feature extraction network, used for extracting features from the information of the gas equipment to be stored to obtain a first feature; A second feature extraction network is used to extract features from the storage environment information to obtain a second feature; A feature fusion network, used for fusing the first feature and the second feature to obtain a fused feature; The output network is used to output the probability distribution of the storage location of the gas equipment to be stored in the warehouse based on the fusion feature.

4. The warehouse logistics management method according to claim 3, characterized in that: The first feature extraction network comprises: The input layer, embedding layer, position encoding, self-attention mechanism, multi-head attention mechanism, memory unit, context-aware module, convolution layer and adaptive pooling layer are connected in sequence.

5. The warehouse logistics management method according to claim 3, characterized in that: The second feature extraction network includes: Input layer, first LSTM layer, second LSTM layer, fully connected layer, and output layer.

6. The warehouse logistics management method according to claim 3, characterized in that: The feature fusion network includes the following connected in sequence: Feature fusion layer, first fully connected layer, second fully connected layer, activation function.

7. The warehouse logistics management method according to claim 1, characterized in that: The gas equipment storage management model is trained through the following steps: Collect equipment information of different gas equipment and various environmental information in the warehouse to obtain an information data set, and divide the information data set into a training set and a verification set; Setting training parameters, and using the training set to train the gas equipment storage management model until a maximum number of training times is reached; The trained gas equipment storage management model is verified using the validation set, and is used as a model performance evaluation indicator. When each indicator meets the preset value, the model is verified; otherwise, the training parameters are reset or the training samples in the training set are expanded until the model is verified.

8. A gas equipment storage management device based on industrial Internet of Things, characterized in that: The device comprises: A collection module, used to collect equipment information and storage environment information of the gas equipment to be stored; A preprocessing module, used for preprocessing the equipment information and environment information of the gas equipment to be stored; Model building and training module, used to build and train gas equipment storage management models; The output module analyzes the preprocessed equipment information and environmental information of the gas equipment to be stored based on the trained gas equipment storage management model to output the probability distribution of the storage location of the gas equipment to be stored in the warehouse.

9. A storage medium, characterized in that: The method comprises instructions, which, when executed on a computer, enable the computer to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The electronic device comprises: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

Images