Safety production management system

Abstract

The invention belongs to the technical field of safety production management, and discloses a safety production management system, which comprises a production data processing module used for storing preprocessed production management data into a database; the production equipment management module is used for extracting the operation data of the production equipment from the database and predicting the health state of each piece of production equipment based on the operation data of the production equipment; the oil depot environment management module is used for analyzing an oil quantity change trend according to the oil depot environment monitoring data; and the production risk control management module is used for formulating and implementing risk control measures in combination with the abnormal behaviors of the personnel in the production field and the potential operation risk factors. Based on periodic law and trend analysis, the future deformation and settlement trend of the oil storage tank can be predicted, and then potential problems of the oil storage tank can be found in time.

Description

Technical Field

[0001] The present invention relates to the technical field of production safety management, and in particular to a production safety management system. Background Art

[0002] Safety production in oil tank management is a comprehensive system project, which aims to ensure the safe operation of oil depots, prevent accidents, and protect employees and the environment. Safety production management of oil depots is a complex and important task. It needs to start from multiple aspects, formulate a sound management system, ensure the normal operation of facilities and equipment, strictly abide by operating procedures, strengthen emergency response and safety records and reporting work to ensure the safe operation of oil depots.

[0003] Oil storage tanks are large containers for storing oil products. They have a relatively regular shape and are widely used in refineries, oil fields, oil depots and other industries. The volume of oil storage tanks can range from tens of cubic meters to tens of thousands of cubic meters to meet storage needs of various scales. Oil storage tanks are important facilities for oil storage and have various types and structural characteristics. At the same time, strict safety management is required to ensure their normal operation and safety.

[0004] In the prior art, when conducting safe production management of oil depots, it is impossible to predict the deformation and settlement trends of oil storage tanks based on the oil depot environmental monitoring data, making it difficult to identify and deal with potential problems during the operation of oil storage tanks, and thus it is impossible to take targeted preventive measures in a timely manner, increasing the probability of safety accidents.

[0005] Therefore, how to provide a safe production management system is a problem that needs to be solved urgently. Summary of the invention

[0006] The embodiment of the present invention provides a safe production management system to solve the problem in the prior art that the deformation and settlement trends of oil storage tanks cannot be predicted based on oil depot environmental monitoring data.

[0007] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended to be a general review, nor is it intended to identify key / important components or to delineate the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0008] According to a first aspect of an embodiment of the present invention, a production safety management system is provided.

[0009] In one embodiment, the safety production management system includes:

[0010] The production data processing module is used to collect production management data in real time and perform preprocessing, and store the preprocessed production management data in the database;

[0011] The production equipment management module is used to extract the production equipment operation data from the database and predict the health status of each production equipment based on the production equipment operation data;

[0012] The oil depot environment management module is used to analyze the oil volume change trend based on the oil depot environment monitoring data, and formulate the oil product priority entry and exit plan based on the oil volume change trend;

[0013] The production risk control management module is used to formulate and implement risk control measures based on abnormal behavior of personnel at the production site and potential operational risk factors.

[0014] In one embodiment, the production management data at least includes production equipment operation data, production equipment maintenance data, oil depot environment monitoring data, oil product inventory management data, production personnel management data and financial management data.

[0015] In one embodiment, the production data processing module includes: a production data acquisition module, a production data storage module, a production data scheduling module and a production data access management module, wherein:

[0016] The production data acquisition module is used to collect the production management data in the production process in real time, and transmit the production management data to the production data storage module through the communication network after pre-processing;

[0017] A production data storage module, used to divide the production management data according to the importance of the production management data, and store the divided production management data in a hierarchical manner in a database;

[0018] The production data scheduling module is used to execute the scheduling and allocation between production management data at all levels, and realize the load balancing between production management data at all levels;

[0019] The production data access management module is used to constrain production management data requirements and gradually authorize access rights based on the visitor's identity and behavior.

[0020] In one embodiment, the production data scheduling module includes:

[0021] According to the importance of production management data at all levels, a dual optimization function of data scheduling time and data response time is constructed, and the optimal balance point between data scheduling time and data response time is generated;

[0022] Establish a cloud data collaborative scheduling model under target constraints, and combine the optimal balance point and the cloud data collaborative scheduling model to calculate the load balancing state parameters between production management data at all levels and determine the load balancing threshold;

[0023] Based on the load balancing threshold between production management data at all levels, the scheduling allocation between production management data at all levels is executed to achieve load balancing between production management data at all levels.

[0024] In one embodiment, the production equipment management module includes: a hazard source monitoring and early warning module, an oil storage tank deformation and settlement identification module and an electrostatic grounding status monitoring module, wherein:

[0025] Hazard source monitoring and early warning module, used to analyze and identify potential hazards in production equipment, conduct risk assessment on potential hazards, and formulate emergency measures based on the risk assessment results;

[0026] The oil tank deformation and settlement identification module is used to analyze the deformation and settlement trends of the oil tank and comprehensively evaluate the health status of the oil tank based on the analysis results;

[0027] The electrostatic grounding status online monitoring module is used to extract the electrostatic grounding status based on the electrostatic grounding data of the production equipment and evaluate whether the electrostatic grounding status of the production equipment meets the safety standards.

[0028] In one embodiment, the oil tank deformation and settlement identification module analyzes the deformation and settlement trends of the oil tank and comprehensively evaluates the health status of the oil tank based on the analysis results, including:

[0029] Extract the structural data of the oil storage tank from the oil depot environmental monitoring data, and use the finite element technology to establish the finite element model of the oil storage tank; perform finite element simulation on the oil storage tank under different load conditions to generate the stress distribution of the oil storage tank under different load conditions;

[0030] Extract historical monitoring data of oil storage tanks to construct time series data sets, identify time anomalies in the time series data sets, and eliminate the interference of occasional interference factors on stress distribution;

[0031] The time series data set was analyzed to obtain the periodicity pattern, and a seasonal autoregressive integrated moving average model was established to conduct seasonal analysis on the deformation and settlement trends of oil storage tanks;

[0032] Combined with the stress distribution and seasonal analysis results of oil storage tanks under different load conditions, the Bayesian network is used to perform probabilistic inference on the deformation and settlement of oil storage tanks, and the health status of oil storage tanks is evaluated based on the probabilistic inference results.

[0033] In one embodiment, the analyzing of the time series data set to obtain the periodicity law and establishing the seasonal autoregressive integrated moving average model to perform seasonal analysis on the deformation and settlement trend of the oil storage tank includes:

[0034] Apply Fourier transform to the time series data set to convert the time domain signal into the frequency domain signal and obtain the spectrum distribution; perform wavelet transform on the signal part that cannot be resolved by Fourier transform to obtain the time-frequency distribution diagram;

[0035] Analyze the abnormal changes of signals before and after the deformation and settlement of the oil storage tank according to the time-frequency distribution diagram; extract the frequency domain characteristics by combining the results of Fourier transform and wavelet transform, and perform pattern matching on the extracted frequency domain characteristics;

[0036] The periodic laws in the time series data set are identified through pattern matching of frequency domain characteristics, and a seasonal autoregressive integrated moving average model is established to identify the deformation and settlement trends of oil storage tanks.

[0037] In one embodiment, the expression of the seasonal autoregressive integrated moving average model is:

[0038] Φp(B s )φp(B)(1-B) d (1-B s ) D Y t =Θ Q (B s )θ q (B)ε t ;

[0039] Where Y t represents time series data; B represents the backshift operator; Φp(B s ) represents the seasonal autoregressive polynomial; φp(B) represents the seasonal autoregressive polynomial; Θ Q (B s ) represents the seasonal moving average polynomial; θ q (B) represents the non-seasonal moving average polynomial; ε t represents the white noise error term; p represents the non-seasonal autoregressive order; d represents the non-seasonal difference order, q represents the non-seasonal moving average order; P represents the seasonal autoregressive order; D represents the seasonal difference order; Q represents the seasonal moving average order; s represents the length of the seasonal cycle.

[0040] In one embodiment, the production risk control management module includes: a personnel behavior management module, an operation inspection module and a risk control measures formulation module, wherein:

[0041] The personnel behavior management module is used to identify the characteristic information of the personnel at the production site and judge the abnormal behavior of the personnel at the production site based on the characteristic information of the personnel at the production site;

[0042] The operation inspection module is used to conduct regular and random inspections of the production site according to the preset inspection plan and analyze potential operation risk factors in the production site;

[0043] The risk control measures formulation module is used to formulate risk control measures and continuously optimize and improve risk control measures based on implementation results.

[0044] In one embodiment, the personnel behavior management module includes: identifying characteristic information of personnel at the production site and determining abnormal behavior of personnel at the production site based on the characteristic information of personnel at the production site;

[0045] Extract real-time image data of the production site, and segment the human features of the personnel on the production site from the real-time image data;

[0046] Input human body features into a pre-built human joint point detection model, track human joint points through the human joint point detection model, and obtain a joint point heat map;

[0047] Extract the coordinates of the human joints from the joint heat map, and use the coordinates of the joints to input them into the variant recurrent neural network frame by frame in time sequence. At the same time, add the output of the GRU layer of the first branch and the output of the flattening layer of the second branch in the variant recurrent neural network and input them into the classifier for classification.

[0048] The human behavior output by the classifier is compared with the normal behavior pattern, and the abnormal behavior of personnel at the production site is identified based on the comparison results.

[0049] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0050] 1. The present invention collects production management data in real time, facilitates the analysis of equipment operation data to predict the health status of equipment, and can achieve preventive maintenance. At the same time, by analyzing environmental monitoring data, it can predict the trend of oil volume changes and identify potential sources of danger, thereby helping to avoid serious accidents such as oil depot leakage and fire. Through real-time data monitoring, predictive analysis and early warning mechanisms, it provides all-round support for the safe production of oil depots.

[0051] 2. The present invention predicts the health status of equipment by analyzing the operating data of production equipment, which can achieve early warning. The finite element model and historical data analysis are used to improve the analysis accuracy of deformation and settlement of oil storage tanks. By eliminating occasional interference factors and identifying abnormal points in time series, the possibility of false alarms and missed alarms is reduced. At the same time, based on periodic laws and trend analysis, the future deformation and settlement trends of oil storage tanks can be predicted, and potential problems of oil storage tanks can be discovered in time, thereby extending the service life of oil storage tanks.

[0052] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0054] Figure 1 is a principle block diagram of a production safety management system according to an exemplary embodiment;

[0055] Figure 2 is a flow chart of a safety production management method according to an exemplary embodiment;

[0056] Figure 3 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0057] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0058] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0059] As used herein, the term "plurality" means two or more than two, unless otherwise specified.

[0060] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0061] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.

[0062] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0063] Each module in the device or production safety management system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.

[0064] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0065] Figure 1An embodiment of a production safety management system of the present invention is shown.

[0066] In this optional embodiment, the safety production management system includes:

[0067] The production data processing module 101 is used to collect production management data in real time and perform preprocessing, and store the preprocessed production management data in a database;

[0068] The production equipment management module 103 is used to extract the production equipment operation data from the database and predict the health status of each production equipment based on the production equipment operation data;

[0069] The oil depot environment management module 105 is used to analyze the oil quantity change trend according to the oil depot environment monitoring data, and formulate the oil product priority entry and exit plan according to the oil quantity change trend;

[0070] The production risk control management module 107 is used to formulate and implement risk control measures based on abnormal behaviors of personnel at the production site and potential operational risk factors.

[0071] In this optional embodiment, the production management data includes at least production equipment operation data, production equipment maintenance data, oil depot environment monitoring data, oil product inventory management data, production personnel management data and financial management data.

[0072] In this optional embodiment, the production data processing module includes: a production data acquisition module, a production data storage module, a production data scheduling module and a production data access management module, wherein:

[0073] The production data acquisition module is used to collect the production management data in the production process in real time, and transmit the production management data to the production data storage module through the communication network after pre-processing;

[0074] A production data storage module, used to divide the production management data according to the importance of the production management data, and store the divided production management data in a hierarchical manner in a database;

[0075] The production data scheduling module is used to execute the scheduling and allocation between production management data at all levels, and realize the load balancing between production management data at all levels;

[0076] The production data access management module is used to constrain production management data requirements and gradually authorize access rights based on the visitor's identity and behavior.

[0077] In this optional embodiment, the production data scheduling module includes:

[0078] According to the importance of production management data at all levels, a dual optimization function of data scheduling time and data response time is constructed, and the optimal balance point between data scheduling time and data response time is generated; a cloud data collaborative scheduling model under target constraints is established, and the load balancing state parameters between production management data at all levels are calculated in combination with the optimal balance point and the cloud data collaborative scheduling model, and the load balancing threshold is determined; based on the load balancing threshold between production management data at all levels, scheduling allocation between production management data at all levels is executed to achieve load balancing between production management data at all levels.

[0079] In this optional embodiment, the production equipment management module includes: a hazard source monitoring and early warning module, an oil storage tank deformation and settlement identification module and an electrostatic grounding state monitoring module, wherein:

[0080] Hazard source monitoring and early warning module, used to analyze and identify potential hazards in production equipment, conduct risk assessment on potential hazards, and formulate emergency measures based on the risk assessment results;

[0081] The oil tank deformation and settlement identification module is used to analyze the deformation and settlement trends of the oil tank and comprehensively evaluate the health status of the oil tank based on the analysis results;

[0082] The electrostatic grounding status online monitoring module is used to extract the electrostatic grounding status based on the electrostatic grounding data of the production equipment and evaluate whether the electrostatic grounding status of the production equipment meets the safety standards.

[0083] In this optional embodiment, the analyzing and identifying potential hazards in the production equipment, performing risk assessment on the potential hazards, and formulating emergency measures based on the risk assessment results include:

[0084] Collect production equipment operating parameter data, and identify potential hazard source data from the production equipment operating parameter data; combine potential hazard source data with hazard and operability analysis technology to establish a hazard source assessment model; input the identified potential hazard source data into the hazard source assessment model, calculate its occurrence probability and severity, and grade the assessment results to determine the risk level, such as high risk level, medium risk level and low risk level; set the warning threshold according to the risk assessment results. When the real-time data triggers the warning threshold, the system automatically generates warning information and notifies relevant personnel.

[0085] In this optional embodiment, the oil tank deformation and settlement identification module includes:

[0086] The structural data of the oil storage tank is extracted from the oil depot environmental monitoring data, and the finite element model of the oil storage tank is established using finite element technology; finite element simulation is performed on the oil storage tank under different load conditions to generate the stress distribution of the oil storage tank under different load conditions; the historical monitoring data of the oil storage tank is extracted to construct a time series data set, the time anomalies in the time series data set are identified, and the interference of occasional interference factors on the stress distribution is eliminated; the time series data set is analyzed to obtain the periodic law, and a seasonal autoregressive integrated moving average model is established to perform seasonal analysis on the deformation and settlement trends of the oil storage tank; combined with the stress distribution of the oil storage tank under different load conditions and the seasonal analysis results, the Bayesian network is used to perform probabilistic inference on the deformation and settlement of the oil storage tank, and the health status of the oil storage tank is evaluated based on the probabilistic inference results.

[0087] In this optional embodiment, the analysis of the time series data set to obtain the periodicity law and the establishment of a seasonal autoregressive integrated moving average model to perform seasonal analysis on the deformation and settlement trends of the oil storage tank include:

[0088] Fourier transform is applied to the time series data set to convert the time domain signal into frequency domain signal and obtain the spectrum distribution; wavelet transform is performed on the signal part that cannot be resolved by Fourier transform to obtain the time-frequency distribution diagram; the abnormal changes of the signal before and after the deformation and settlement of the oil storage tank are analyzed according to the time-frequency distribution diagram; the frequency domain characteristics are extracted by combining the results of Fourier transform and wavelet transform, and the extracted frequency domain characteristics are pattern matched; the periodic laws in the time series data set are identified through pattern matching of frequency domain characteristics, and a seasonal autoregressive integrated moving average model is established to identify the deformation and settlement trends of the oil storage tank.

[0089] In this optional embodiment, the expression of the seasonal autoregressive integrated moving average model is:

[0090] Φp(B s )φp(B)(1-B) d (1-B s ) D Y t =Θ Q (B s )θ q (B)ε t ;

[0091] Where Y t represents time series data; B represents the backshift operator; Φp(B s ) represents the seasonal autoregressive polynomial; φp(B) represents the seasonal autoregressive polynomial; Θ Q (B s ) represents the seasonal moving average polynomial; θ q (B) represents the non-seasonal moving average polynomial; ε trepresents the white noise error term; p represents the non-seasonal autoregressive order; d represents the non-seasonal difference order, q represents the non-seasonal moving average order; P represents the seasonal autoregressive order; D represents the seasonal difference order; Q represents the seasonal moving average order; s represents the length of the seasonal cycle.

[0092] In this optional embodiment, the production risk control management module includes: a personnel behavior management module, an operation inspection module and a risk control measures formulation module, wherein:

[0093] The personnel behavior management module is used to identify the characteristic information of the personnel at the production site and judge the abnormal behavior of the personnel at the production site based on the characteristic information of the personnel at the production site;

[0094] The operation inspection module is used to conduct regular and random inspections of the production site according to the preset inspection plan and analyze potential operation risk factors in the production site;

[0095] The risk control measures formulation module is used to formulate risk control measures and continuously optimize and improve risk control measures based on implementation results.

[0096] In this optional embodiment, the personnel behavior management module includes:

[0097] Real-time image data of the production site is extracted, and the human features of the personnel on the production site are segmented from the real-time image data; the human features are input into a pre-built human joint detection model, and the human joints are tracked through the human joint detection model to obtain a joint heat map; the coordinates of the human joints are extracted from the joint heat map, and the joint coordinates are input into the variant recurrent neural network frame by frame in time sequence, and at the same time, the GRU layer output of the first branch of the variant recurrent neural network and the flattening layer output of the second branch are added and input into the classifier for classification; the human behavior output by the classifier is compared with the normal behavior pattern, and the abnormal behavior of the personnel on the production site is identified based on the comparison result.

[0098] In this optional embodiment, the Variant Recurrent Neural Network (VRNN) is a model that combines the Variational Autoencoder (VAE) and the Recurrent Neural Network (RNN). When processing time series data or sequence generation tasks, it can better capture the complex dependencies in the sequence data, which mainly includes:

[0099] Collect and preprocess time series data, and design the structure of VRNN, including input layer, encoder, latent variables, decoder and output layer; at each time step, use the encoder to generate the parameters (mean and variance) of the latent variables, sample from the latent variables, combine the hidden state of the previous time step to generate the output of the current time step, and map the input data to the latent variables through the encoder, and combine the hidden state of RNN to generate the output of the current time step; use reconstruction error and KL divergence (Kullback-Leibler Divergence) as loss functions, and optimize the model parameters through the back propagation algorithm to minimize the loss function, and then use the validation set to evaluate the model performance, adjust the model architecture and hyperparameters.

[0100] Figure 2 An embodiment of a safe production management method of the present invention is shown.

[0101] In this optional embodiment, the safety production management method includes:

[0102] Step S201, real-time collection of production management data and preprocessing, and storing the preprocessed production management data in a database;

[0103] Step S203, extracting the production equipment operation data from the database, and predicting the health status of each production equipment based on the production equipment operation data;

[0104] Step S205, analyzing the oil quantity change trend according to the oil depot environmental monitoring data, and formulating a priority oil in and out plan based on the oil quantity change trend;

[0105] Step S207, formulate and implement risk control measures based on abnormal behaviors of personnel at the production site and potential operational risk factors.

[0106] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0107] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0108] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0109] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0110] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0111] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A production safety management system, characterized in that: The safety production management system includes: The production data processing module is used to collect production management data in real time and perform preprocessing, and store the preprocessed production management data in the database; The production equipment management module is used to extract the production equipment operation data from the database and predict the health status of each production equipment based on the production equipment operation data; The oil depot environment management module is used to analyze the oil volume change trend based on the oil depot environment monitoring data, and formulate the oil product priority entry and exit plan based on the oil volume change trend; The production risk control management module is used to formulate and implement risk control measures based on abnormal behavior of personnel at the production site and potential operational risk factors.

2. A production safety management system according to claim 1, characterized in that: The production management data at least includes production equipment operation data, production equipment maintenance data, oil depot environment monitoring data, oil product inventory management data, production personnel management data and financial management data.

3. A production safety management system according to claim 2, characterized in that: The production data processing module includes: a production data acquisition module, a production data storage module, a production data scheduling module and a production data access management module, wherein: The production data acquisition module is used to collect the production management data in the production process in real time, and transmit the production management data to the production data storage module through the communication network after pre-processing; A production data storage module, used to divide the production management data according to the importance of the production management data, and store the divided production management data in a hierarchical manner in a database; The production data scheduling module is used to execute the scheduling and allocation between production management data at all levels, and realize the load balancing between production management data at all levels; The production data access management module is used to constrain production management data requirements and gradually authorize access rights based on the visitor's identity and behavior.

4. A production safety management system according to claim 3, characterized in that: The production data scheduling module includes: According to the importance of production management data at all levels, a dual optimization function of data scheduling time and data response time is constructed, and the optimal balance point between data scheduling time and data response time is generated; Establish a cloud data collaborative scheduling model under target constraints, and combine the optimal balance point and the cloud data collaborative scheduling model to calculate the load balancing state parameters between production management data at all levels and determine the load balancing threshold; Based on the load balancing threshold between production management data at all levels, the scheduling allocation between production management data at all levels is executed to achieve load balancing between production management data at all levels.

5. A production safety management system according to claim 4, characterized in that: The production equipment management module includes: a hazard source monitoring and early warning module, an oil storage tank deformation and settlement identification module and an electrostatic grounding status monitoring module, wherein: Hazard source monitoring and early warning module, used to analyze and identify potential hazards in production equipment, conduct risk assessment on potential hazards, and formulate emergency measures based on the risk assessment results; The oil tank deformation and settlement identification module is used to analyze the deformation and settlement trends of the oil tank and comprehensively evaluate the health status of the oil tank based on the analysis results; The electrostatic grounding status online monitoring module is used to extract the electrostatic grounding status based on the electrostatic grounding data of the production equipment and evaluate whether the electrostatic grounding status of the production equipment meets the safety standards.

6. A production safety management system according to claim 5, characterized in that: The oil tank deformation and settlement identification module includes: Extract the structural data of the oil storage tank from the oil depot environmental monitoring data, and use the finite element technology to establish the finite element model of the oil storage tank; perform finite element simulation on the oil storage tank under different load conditions to generate the stress distribution of the oil storage tank under different load conditions; Extract historical monitoring data of oil storage tanks to construct time series data sets, identify time anomalies in the time series data sets, and eliminate the interference of occasional interference factors on stress distribution; The time series data set was analyzed to obtain the periodicity pattern, and a seasonal autoregressive integrated moving average model was established to conduct seasonal analysis on the deformation and settlement trends of oil storage tanks; Combined with the stress distribution and seasonal analysis results of oil storage tanks under different load conditions, the Bayesian network is used to perform probabilistic inference on the deformation and settlement of oil storage tanks, and the health status of oil storage tanks is evaluated based on the probabilistic inference results.

7. A production safety management system according to claim 6, characterized in that: The analysis of the time series data set to obtain periodicity and establish a seasonal autoregressive integrated moving average model to perform seasonal analysis on the deformation and settlement trends of the oil storage tank include: Apply Fourier transform to the time series data set to convert the time domain signal into the frequency domain signal and obtain the spectrum distribution; perform wavelet transform on the signal part that cannot be resolved by Fourier transform to obtain the time-frequency distribution diagram; Analyze the abnormal changes of signals before and after the deformation and settlement of the oil storage tank according to the time-frequency distribution diagram; extract the frequency domain characteristics by combining the results of Fourier transform and wavelet transform, and perform pattern matching on the extracted frequency domain characteristics; The periodic laws in the time series data set are identified through pattern matching of frequency domain characteristics, and a seasonal autoregressive integrated moving average model is established to identify the deformation and settlement trends of oil storage tanks.

8. A production safety management system according to claim 7, characterized in that: The expression of the seasonal autoregressive integrated moving average model is: Φp(B s )φp(B)(1-B) d (1-B s ) D Y t =Θ Q (B s )θ q (B)ε t ; Where Y t represents time series data; B represents the backshift operator; Φp(B s ) represents the seasonal autoregressive polynomial; φp(B) represents the seasonal autoregressive polynomial; Θ Q (B s ) represents the seasonal moving average polynomial; θ q (B) represents the non-seasonal moving average polynomial; ε t represents the white noise error term; p represents the non-seasonal autoregressive order; d represents the non-seasonal difference order, q represents the non-seasonal moving average order; P represents the seasonal autoregressive order; D represents the seasonal difference order; Q represents the seasonal moving average order; s represents the length of the seasonal cycle.

9. A production safety management system according to claim 8, characterized in that: The production risk control management module includes: personnel behavior management module, operation inspection module and risk control measures formulation module, among which: The personnel behavior management module is used to identify the characteristic information of the personnel at the production site and judge the abnormal behavior of the personnel at the production site based on the characteristic information of the personnel at the production site; The operation inspection module is used to conduct regular and random inspections of the production site according to the preset inspection plan and analyze potential operation risk factors in the production site; The risk control measures formulation module is used to formulate risk control measures and continuously optimize and improve risk control measures based on implementation results.

10. A production safety management system according to claim 9, characterized in that: The personnel behavior management module includes: identifying characteristic information of personnel at the production site, and judging abnormal behavior of personnel at the production site based on the characteristic information of personnel at the production site; Extract real-time image data of the production site, and segment the human features of the personnel on the production site from the real-time image data; Input human body features into a pre-built human joint point detection model, track human joint points through the human joint point detection model, and obtain a joint point heat map; Extract the coordinates of the human joints from the joint heat map, and use the coordinates of the joints to input them into the variant recurrent neural network frame by frame in time sequence. At the same time, add the output of the GRU layer of the first branch and the output of the flattening layer of the second branch in the variant recurrent neural network and input them into the classifier for classification. The human behavior output by the classifier is compared with the normal behavior pattern, and the abnormal behavior of personnel at the production site is identified based on the comparison results.

Images