Chemical operation risk monitoring method and device, storage medium and electronic equipment

Abstract

The invention provides a risk monitoring method and device for chemical operation, a storage medium and electronic equipment, and the method comprises the steps: obtaining operation bill data and operation field monitoring parameters corresponding to the chemical operation when it is detected that an operation object executes the chemical operation; preprocessing the obtained operation bill data and the operation field detection data to obtain time sequence data of the chemical operation; processing the operation bill data by using a preset rule engine to obtain an initial risk score of the chemical operation; inputting the initial risk score and the time sequence data into a pre-trained time sequence prediction model to obtain a prediction result; the prediction result comprises the change trend of the key parameters of the chemical work at the target time; obtaining the risk increment of the chemical operation according to the prediction result; and obtaining a chemical operation risk monitoring result according to the initial risk score, the prediction result and the dynamic risk increment. And a comprehensive and accurate risk monitoring result can be obtained.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, storage medium and electronic equipment for risk monitoring of chemical operations. Background Art

[0002] In the modern chemical industry, the safety and reliability of chemical operations are of paramount importance. To ensure safety during operations, various risk monitoring methods and systems are widely used in the existing technology.

[0003] However, existing chemical operation risk monitoring methods often use a single assessment indicator for risk assessment, making the risk monitoring results one-sided and incomplete. Summary of the Invention

[0004] The technical problem to be solved by this application is to provide a risk monitoring method, device, storage medium and electronic equipment for chemical operations, which can quickly and accurately obtain safety monitoring results. The specific solution is as follows:

[0005] A risk monitoring method for chemical operations, comprising:

[0006] When it is detected that the operation object is performing a chemical operation, the operation ticket data corresponding to the chemical operation and the operation site monitoring parameters are obtained;

[0007] Preprocessing the acquired operation ticket data and the operation site detection data to obtain time series data of the chemical operation, wherein the time series data includes key parameters of multiple time steps;

[0008] Processing the operation ticket data using a preset rule engine to obtain an initial risk score for the chemical operation;

[0009] Inputting the initial risk score and the time series data into a pre-trained time series prediction model to obtain a prediction result; the prediction result includes a change trend of key parameters of the chemical operation at the target time;

[0010] Obtaining a risk increment for the chemical operation according to the prediction result;

[0011] The chemical operation risk monitoring result is obtained according to the initial risk score, the prediction result and the dynamic risk increment.

[0012] Optionally, the method described above processes the operation ticket data using a preset rule engine to obtain an initial risk score for the chemical operation, including:

[0013] Obtaining each operation record in the operation ticket data;

[0014] The rule engine is used to match the rules applicable to each operation record in a pre-built rule set to obtain a score for each operation record, and the risk scores of each operation record are accumulated to obtain an initial risk score for the chemical operation.

[0015] Optionally, the above method further comprises obtaining the risk increment of the chemical operation according to the prediction result, including:

[0016] Obtaining actual measurement results of the chemical operation at a target time;

[0017] Calculating a sub-risk increment of each key parameter of the chemical operation according to the actual measurement result and the prediction result;

[0018] The risk increment of the chemical operation is calculated by performing a weighted summation on the sub-risk increments of each of the key parameters.

[0019] In the above method, optionally, the training process of the time series prediction model includes:

[0020] Obtaining an initial model and a training data set; the training data set includes a plurality of training samples; each training sample includes historical operation ticket data and operation site monitoring parameters for a preset time period;

[0021] Training the initial model using the training data set;

[0022] When the initial model meets the preset training conditions, the initial model is used as the trained time series prediction model.

[0023] Optionally, the above method may include the risk monitoring result including an operation risk score. After obtaining the chemical operation risk monitoring result based on the initial risk score, the prediction result, and the dynamic risk increment, the method may further include:

[0024] When the operation risk score is greater than a preset score threshold, an alarm message is output, and the alarm message is used to instruct to stop the chemical operation.

[0025] A chemical operation risk monitoring device, comprising:

[0026] An acquisition unit, configured to acquire operation ticket data and operation site monitoring parameters corresponding to a chemical operation when detecting that the operation object is performing a chemical operation;

[0027] A preprocessing unit, configured to preprocess the acquired operation ticket data and the operation site detection data to obtain time series data of the chemical operation, wherein the time series data includes key parameters of multiple time steps;

[0028] A first execution unit is configured to process the operation ticket data using a preset rule engine to obtain an initial risk score for the chemical operation;

[0029] A second execution unit is configured to input the initial risk score and the time series data into a pre-trained time series prediction model to obtain a prediction result; the prediction result includes a change trend of key parameters of the chemical operation at a target time;

[0030] A third execution unit is configured to obtain a risk increment of the chemical operation according to the prediction result;

[0031] The fourth execution unit is used to obtain the chemical operation risk monitoring result according to the initial risk score, the prediction result and the dynamic risk increment.

[0032] In the above device, optionally, the first execution unit includes:

[0033] A first acquisition subunit is used to acquire each operation record in the operation ticket data;

[0034] The matching subunit is used to use the rule engine to match the rules applicable to each operation record in the pre-built rule set, obtain the score of each operation record, accumulate the risk scores of each operation record, and obtain the initial risk score of the chemical operation.

[0035] The above device, optionally, a third execution unit includes:

[0036] A second acquisition subunit is used to obtain the actual measurement result of the chemical operation at the target time;

[0037] A first calculation subunit is configured to calculate a sub-risk increment of each key parameter of the chemical operation based on the actual measurement result and the prediction result;

[0038] The second calculation subunit is used to perform weighted summation on the sub-risk increments of each of the key parameters to calculate the risk increment of the chemical operation.

[0039] A storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute a risk monitoring method for a chemical operation as described above.

[0040] An electronic device includes a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to implement the above-mentioned risk monitoring method for chemical operations.

[0041] Based on the above-mentioned embodiment of the present application, a risk monitoring method, device, storage medium and electronic device for chemical operations are provided. The method includes: when an operation object is detected to be performing a chemical operation, obtaining operation ticket data and operation site monitoring parameters corresponding to the chemical operation; pre-processing the obtained operation ticket data and the operation site detection data to obtain time series data of the chemical operation, the time series data including key parameters of multiple time steps; using a preset rule engine to process the operation ticket data to obtain an initial risk score of the chemical operation; inputting the initial risk score and the time series data into a pre-trained time series prediction model to obtain a prediction result; the prediction result includes the change trend of the key parameters of the chemical operation at the target time; obtaining the risk increment of the chemical operation based on the prediction result; obtaining the risk monitoring result of the chemical operation based on the initial risk score, the prediction result and the dynamic risk increment. In the method provided in this embodiment, by comprehensively using the operation ticket data and the operation site monitoring parameters, the time series data is generated after pre-processing, and the initial risk score is calculated using the rule engine, and then the change trend of the key parameters is obtained by combining the pre-trained time series prediction model, and finally the initial risk score, the prediction result and the dynamic risk increment are integrated to obtain the risk monitoring result of the chemical operation. This systematic process not only improves the accuracy and real-time nature of risk assessments, but also enables timely identification of potential risks and provision of early warnings, thereby significantly enhancing the safety and reliability of chemical operations, effectively preventing accidents, and ensuring the stable operation of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0043] Figure 1 A flow chart of a method for risk monitoring of chemical operations provided in this application;

[0044] Figure 2 A flowchart of a process for obtaining an initial risk score for a chemical operation provided in this application;

[0045] Figure 3 A flowchart of a process for obtaining a risk increment for a chemical operation based on prediction results provided in this application;

[0046] Figure 4A schematic diagram of the structure of a chemical operation risk monitoring device provided in this application;

[0047] Figure 5 This is a schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0049] In this application, the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0050] The embodiment of the present application provides a risk monitoring method for chemical operations, which can be applied to electronic devices, such as computers, smart phones, tablet devices, smart wearable devices, server clusters or cloud computing centers, etc. The method flow chart of the method is as follows: Figure 1 As shown, specifically including:

[0051] S101: When it is detected that the operation object performs a chemical operation, operation ticket data and operation site monitoring parameters corresponding to the chemical operation are obtained.

[0052] In this embodiment, the front-end sensor network can be first deployed at the work site to obtain the work site monitoring parameters; then the middleware platform is deployed to collect, process and transmit data from the sensors, and interact with the work management system to obtain work ticket information.

[0053] Optionally, on-site monitoring parameters cover a variety of physical and chemical quantities closely related to the safety and efficiency of chemical operations, including but not limited to at least one of the following: temperature, pressure, gas concentration, liquid level, flow rate, pH value, vibration, conductivity, optical properties, chemical composition analysis, humidity, video monitoring, sound monitoring, and equipment status monitoring. Real-time data on these parameters (such as temperature readings, pressure change rate, gas concentration, liquid level height, flow rate, etc.) is collected through a sensor network to ensure the safety and stability of operations. For example, temperature and pressure monitoring can prevent risks caused by overheating or overpressure; gas concentration monitoring helps avoid toxic and hazardous gas leaks or explosions; and liquid level and flow control ensure the proper management of reactants and products. Comprehensive and accurate monitoring of these key parameters can promptly detect and respond to potential safety hazards, thereby improving the overall safety and reliability of chemical operations.

[0054] Optionally, the work ticket data corresponding to chemical operations covers key information required to ensure safe, compliant, and efficient execution of the operations, including but not limited to at least one of the following: operation type (such as synthesis reaction, separation and purification, etc.), properties of the chemicals involved (such as toxicity, flammability, corrosiveness, and their specific composition), equipment configuration and status (such as the type and specifications of the reactor used, and maintenance records), operator qualifications and training (such as operator certificates and training completion status), historical accident or abnormal event records (for reference and preventive measures), operation schedule (start time and expected end time), safety measures and emergency plans (such as personal protective equipment requirements, emergency evacuation routes), and compliance with relevant regulations and standards. This data is managed and stored through operation management systems (such as ERP and MES), providing important static background information for risk assessment, real-time monitoring, and post-analysis, ensuring that each chemical operation is carried out under controlled and safe conditions.

[0055] In this embodiment, when a start signal or event is detected, it can be determined that the operation object is performing a chemical operation.

[0056] Optionally, the start signal may include: a signal from an operator submitting a new job request via a mobile application or a fixed terminal; a signal from a specific device starting up or entering operational mode (which can be detected by a PLC or other automated control system); or a signal from an on-site sensor detecting an abnormal change (such as a sudden temperature rise or pressure surge).

[0057] In this embodiment, an API interface is used to connect to existing job management systems (such as ERP and MES) to ensure that relevant job ticket data can be automatically retrieved when a job is detected to have started. The obtained job ticket is parsed to extract necessary static information, such as the operation type, chemicals involved, and equipment configuration.

[0058] In this embodiment, a message queue (such as Kafka, RabbitMQ) or a database table can be used to cache real-time incoming monitoring data to ensure data integrity. An accurate timestamp is added to each piece of data so that the data source can be accurately traced during subsequent analysis.

[0059] S102: Preprocessing the acquired operation ticket data and the operation site detection data to obtain time series data of the chemical operation, where the time series data includes key parameters of multiple time steps.

[0060] In this example, preprocessing the acquired work ticket data and on-site inspection data is a key step in ensuring the accuracy of subsequent analysis. First, data quality is ensured by cleaning the data to remove noise, outliers, and missing values. Next, static information in the work ticket (such as operation type and chemical properties) is combined with key parameters monitored in real time (such as temperature, pressure, and gas concentration) to create a complete data record for each time point. These data records are arranged in chronological order to form a time series dataset, where each time step contains the measured values ​​of multiple key parameters.

[0061] S103: Processing the operation ticket data using a preset rule engine to obtain an initial risk score for the chemical operation.

[0062] In this embodiment, data collection and preparation can be performed first. Key information is extracted from documents such as work permits, safety data sheets (SDS), training records, etc., including operation type, properties of chemicals involved, equipment status, operator qualifications, and historical accident records. These data form the basis of risk assessment. Then, according to industry standards and internal company policies, a series of rules are formulated to form a rule set, such as increasing risk scores for highly toxic chemicals, and adding extra points to operators who have not completed necessary training. A rule engine is developed using a programming language or a dedicated tool (such as Drools), which can receive input data and calculate the corresponding risk score based on predefined rules. At the same time, historical data analysis is integrated to adjust the rules to ensure that they reflect the actual situation.

[0063] During the data mapping and conversion phase, we ensure that the information in the job ticket correctly maps to the conditions of the rule model and standardize the data format for efficient processing by the rule engine. The rule engine then traverses all applicable rules in the rule set, accumulates the corresponding scores, and generates a comprehensive risk score. We set reasonable baselines and warning thresholds to compare the relative risks of different jobs and trigger necessary reviews or preventative measures.

[0064] In some embodiments, after obtaining an initial risk score, a report containing the preliminary risk score can be generated for reference by the managed entity. The effectiveness of the rules can be regularly evaluated, and the rule model can be continuously optimized based on new information and technological advances. This systematic process allows for an accurate assessment of the initial risk of each chemical operation, providing a solid foundation for subsequent dynamic risk monitoring. Specifically, a report containing the initial risk score can be output, and upon receiving a rule update request from the managed entity based on the initial risk score report, the rule set can be updated accordingly.

[0065] In one embodiment provided in the present application, based on the above solution, optionally, the process of processing the operation ticket data using a preset rule engine to obtain the initial risk score of the chemical operation is as follows: Figure 2 As shown, including:

[0066] S201: Acquire each job record in the job ticket data.

[0067] In this embodiment, each operation record may be obtained first, which includes information such as the operation type, properties of the chemicals involved, equipment status, operator qualifications, and historical accidents.

[0068] S202: Using the rule engine to match the rules applicable to each operation record in the pre-built rule set, obtain a score for each operation record, and accumulate the risk scores of each operation record to obtain an initial risk score for the chemical operation.

[0069] Optionally, the rule engine matches each operation record with a pre-built rule set, identifies the specific rules applicable to the record, and calculates the corresponding score based on the matching results. The rule engine then accumulates the risk scores of all operation records to obtain the initial risk score R for the entire chemical operation. initial This process ensures that every operational detail is fully evaluated, and by accumulating the scores of each record, a comprehensive risk score is ultimately formed, providing a solid foundation for subsequent dynamic risk assessment.

[0070] S104: Inputting the initial risk score and the time series data into a pre-trained time series prediction model to obtain a prediction result; the prediction result includes a change trend of key parameters of the chemical operation at the target time.

[0071] In this embodiment, the initial risk score and time series data can be input into a pre-trained time series prediction model. The initial risk score provides a baseline risk level for the operation, while the time series data contains historical measurements of key parameters (such as temperature, pressure, and gas concentration). These data serve as inputs to the model, which determines the changing trends of key parameters of the chemical operation at a target time, which can be a time point or time period after the current time point.

[0072] Optionally, a time series forecasting model uses input time series data to capture underlying patterns and structures through machine learning algorithms (such as LSTM and GRU). The model not only considers the current data point but also incorporates historical data features such as mean, variance, trend, and cyclical components to enhance forecast accuracy.

[0073] Optionally, the initial risk score R initial As the input of the time series forecasting model, it significantly improves the accuracy and contextual awareness of the forecast. The initial risk score is based on the basic risk level assessed based on static information (such as operation type, chemical properties, equipment status, etc.), which provides important background information for the model, enabling it to more sensitively capture potential safety hazards. Combined with the historical changes in key parameters in the time series data, the model can not only better understand the risk status of the current operation, but also make more reasonable predictions under different operating conditions. In addition, the initial risk score serves as a baseline to help identify key parameter changes that are truly worthy of attention, thereby improving risk management decisions, providing a comprehensive data perspective, and ensuring the safety and reliability of chemical operations.

[0074] In this embodiment, the prediction output by the model includes the trend of changes in key parameters of the chemical operation at the target time. For example, it can predict temperature changes, pressure fluctuations, or changes in gas concentration within a specific time period in the future. Specifically, machine learning or deep learning models are used to predict changes in key parameters over a period of time in the future. For example, LSTM (Long Short-Term Memory) can be used to generate predictions for the next k steps:

[0075] P predicted (t+k)=f(T(t),T(t-1),...,T(t-w+1))

[0076] Where w is the time window width, k is the number of prediction steps, and f is the prediction model function.

[0077] In this embodiment, by combining the initial risk score with the time series data and utilizing a pre-trained prediction model, an accurate prediction of the future trend of changes in key parameters can be obtained.

[0078] In one embodiment provided in the present application, based on the above solution, optionally, the training process of the time series prediction model includes:

[0079] Obtaining an initial model and a training data set; the training data set includes a plurality of training samples; each training sample includes historical operation ticket data and operation site monitoring parameters for a preset time period;

[0080] Training the initial model using the training data set;

[0081] When the initial model meets the preset training conditions, the initial model is used as the trained time series prediction model.

[0082] In this example, the training dataset forms the basis for training the time series prediction model. It contains multiple training samples, each of which covers historical work ticket data and worksite monitoring parameters within a preset time period. The historical work ticket data provides static background information such as operation type, chemical properties, and equipment status, while the worksite monitoring parameters record key parameters (such as temperature, pressure, and gas concentration) collected in real time and their changing trends over time.

[0083] The initial model, which is optional, refers to the basic forecasting model structure established before training begins. It is typically built based on algorithms such as LSTM, GRU, or ARIMA. The model's weights and other parameters are initialized at the beginning of training and iteratively adjusted based on the training dataset to optimize performance and minimize forecast error. After determining the model architecture and hyperparameter settings, the initial model is considered trained and confirmed as a trained time series forecasting model after meeting preset training conditions (such as achieving a specific accuracy or completing a certain number of iterations).

[0084] S105: Obtaining a risk increment of the chemical operation according to the prediction result.

[0085] In an embodiment provided in the present application, based on the above solution, optionally, a process of obtaining the risk increment of the chemical operation according to the prediction result is as follows: Figure 3 As shown, including:

[0086] S301: Acquire actual measurement results of the chemical operation at a target time.

[0087] In this embodiment, the actual measurement result P of the chemical operation at the target time is obtained. actual,i Where i represents the i-th key parameter (such as temperature, pressure, gas concentration, etc.). These actual measurement results reflect the real situation at the operation site.

[0088] S302: Calculate the sub-risk increment of each key parameter of the chemical operation according to the actual measurement result and the prediction result.

[0089] According to the actual measurement results P actual,i And the predicted result P predicted，i , calculate the sub-risk increment ΔR for each key parameter i This can be achieved by defining a risk function f1, which quantifies the impact of the difference between the actual value and the predicted value on the risk. The formula can be:

[0090] ΔR i =f1(P actual,i , P predicted，i )

[0091] For example, the sub-risk increment can be calculated using the following specific formula:

[0092] ΔR i =∑ j w j ·f j (P actual,i , P predicted，i )+w c ·C

[0093] Where C is the score of context information, reflecting the risk level under the current operating conditions, and w c is the corresponding weight factor, which determines the importance of contextual information in the entire risk assessment. c , you can control the degree of influence of contextual information on the final risk score. j (P actual,i , P predicted，i ) is the risk assessment subfunction of the jth feature, which is used to calculate the actual measurement result P actual,i And the predicted result P predicted，i The impact of the difference between the two on risk. j It may correspond to different characteristics (such as temperature, pressure, gas concentration, etc.) and may use different calculation methods (such as absolute difference, relative rate of change, nonlinear conversion, etc.). j is the weight factor for the jth feature, reflecting its importance in the overall risk assessment. By adjusting these weights, the model can emphasize or weaken the influence of certain features based on the actual situation. Weights can be determined through cross-validation or other optimization methods.

[0094] Optionally, the context information includes but is not limited to at least one of the following: operation type (such as synthesis reaction, separation and purification), equipment status (such as equipment maintenance records, operating hours), environmental conditions (such as weather conditions, temperature and humidity) and operator qualifications (such as training completion status and experience).

[0095] Assuming we have a chemical reactor operating scenario, the formula can work like this:

[0096] First, the dynamic risk increase is calculated, including: 1. For key parameters such as temperature, pressure, and gas concentration, the difference between the actual measured value and the predicted value is calculated, and the difference is calculated by the predefined sub-function f j 2. Apply the corresponding weight \(w_j\) according to the importance of each parameter and take the weighted sum of the risk increments of all parameters.

[0097] Then, context information is obtained, including: obtaining context information of current operating conditions, such as operation type (synthesis reaction), equipment status (last maintenance date), environmental conditions (workshop temperature and humidity), etc. Calculate the score C of the context information and assign a weight w according to its importance c .

[0098] Finally, the comprehensive risk increment is calculated, including: combining the dynamic risk increment and the context information score to obtain the final risk increment ΔR i .

[0099] In this example, by incorporating contextual information, the formula not only considers the specific impact of short-term parameter changes on risk but also integrates background factors under different operating conditions, making the risk assessment more comprehensive and accurate. This helps to promptly identify and respond to potential risks in complex and dynamic operating environments, improving the safety and reliability of chemical operations.

[0100] S303: Perform weighted summation on the sub-risk increments of each of the key parameters to calculate the risk increment of the chemical operation.

[0101] In this embodiment, the sub-risk increments of all key parameters can be weighted and summed to calculate the total risk increment ΔR of the chemical operation. This can be achieved using the following formula:

[0102]

[0103] Where: n is the number of key parameters. i is the risk weight of the i-th key parameter, reflecting its importance in the overall risk assessment.

[0104] S106: Obtain the chemical operation risk monitoring result according to the initial risk score, the prediction result, and the dynamic risk increment.

[0105] R final =α·R initial +β·ΔR+γ·g(P predicted )

[0106] Among them, α, β and γ are weight coefficients determined by cross-validation, and g(P predicted ) is a nonlinear function used to convert the predicted trend of key parameter changes into risk increments. Here g(P predicted ) not only considers the specific values ​​of the parameters, but also integrates the influence of time series characteristics.

[0107] In one embodiment provided in the present application, based on the above solution, optionally, the risk monitoring result includes an operation risk score, and after obtaining the chemical operation risk monitoring result based on the initial risk score, the prediction result, and the dynamic risk increment, the following steps are further included:

[0108] When the operation risk score is greater than a preset score threshold, an alarm message is output, and the alarm message is used to instruct to stop the chemical operation.

[0109] In this embodiment, after obtaining risk monitoring results for a chemical operation, if the calculated operation risk score exceeds a preset threshold, the system automatically outputs an alarm message, indicating that the chemical operation should be immediately stopped. This mechanism ensures that when potential high-risk situations are detected, preventive measures can be taken promptly to avoid possible accidents or dangerous situations. Specifically, the initial risk score, the predicted results, and the dynamic risk increment jointly determine the final operation risk score. When this score exceeds the set safety threshold, the system triggers an alarm and recommends that the operator suspend the operation for further evaluation and treatment, thereby ensuring the safety and reliability of the operation.

[0110] By applying the method provided in this embodiment, dynamic risk assessment is performed by integrating multiple key parameters. This not only integrates real-time monitoring data to accurately reflect risk changes during the operation process, but also introduces nonlinear influencing factors and a flexible weight adjustment mechanism to improve assessment accuracy and adaptability. In addition, the solution integrates multi-source data and considers contextual information to ensure the comprehensiveness and accuracy of risk assessment. Ultimately, combining the initial risk score calculated by the rule engine and the prediction results of the time series prediction model, the system can intelligently output alarm information and promptly instruct to stop chemical operations when the risk score exceeds the preset threshold, thereby significantly enhancing the safety and reliability of chemical operations, effectively preventing the occurrence of potential accidents, and ensuring the stable operation of the production process.

[0111] and Figure 1 Corresponding to the method described above, the embodiment of the present application also provides a chemical operation risk monitoring device for Figure 1 The specific implementation of the method is shown in the following diagram: Figure 4 As shown, specifically including:

[0112] The acquisition unit 401 is configured to acquire operation ticket data and operation site monitoring parameters corresponding to the chemical operation when it is detected that the operation object is performing the chemical operation;

[0113] A preprocessing unit 402 is configured to preprocess the acquired operation ticket data and the operation site detection data to obtain time series data of the chemical operation, wherein the time series data includes key parameters of multiple time steps;

[0114] The first execution unit 403 is configured to process the operation ticket data using a preset rule engine to obtain an initial risk score for the chemical operation;

[0115] The second execution unit 404 is configured to input the initial risk score and the time series data into a pre-trained time series prediction model to obtain a prediction result; the prediction result includes a change trend of key parameters of the chemical operation at a target time;

[0116] The third execution unit 405 is configured to obtain a risk increment of the chemical operation according to the prediction result;

[0117] The fourth execution unit 406 is configured to obtain the chemical operation risk monitoring result according to the initial risk score, the prediction result, and the dynamic risk increment.

[0118] In an embodiment provided in the present application, based on the above solution, optionally, the first execution unit 403 includes:

[0119] A first acquisition subunit is used to acquire each operation record in the operation ticket data;

[0120] The matching subunit is used to use the rule engine to match the rules applicable to each operation record in the pre-built rule set, obtain the score of each operation record, accumulate the risk scores of each operation record, and obtain the initial risk score of the chemical operation.

[0121] In an embodiment provided in the present application, based on the above solution, optionally, the third execution unit 405 includes:

[0122] A second acquisition subunit is used to obtain the actual measurement result of the chemical operation at the target time;

[0123] A first calculation subunit is configured to calculate a sub-risk increment of each key parameter of the chemical operation based on the actual measurement result and the prediction result;

[0124] The second calculation subunit is used to perform weighted summation on the sub-risk increments of each of the key parameters to calculate the risk increment of the chemical operation.

[0125] In an embodiment provided in the present application, based on the above solution, optionally, the second execution unit 404 includes:

[0126] The third acquisition subunit is used to acquire an initial model and a training data set; the training data set includes a plurality of training samples; each training sample includes historical operation ticket data and operation site monitoring parameters for a preset time period;

[0127] A training subunit, configured to train the initial model using the training data set;

[0128] The execution subunit is used to use the initial model as a trained time series prediction model when the initial model meets the preset training conditions.

[0129] In an embodiment provided in the present application, based on the above solution, optionally, the device further includes:

[0130] The alarm unit is used to output an alarm message when the operation risk score is greater than a preset score threshold, and the alarm message is used to instruct to stop the chemical operation.

[0131] The specific principles and execution processes of each unit and module in the chemical operation risk monitoring device disclosed in the above embodiment of the present application are the same as those of the chemical operation risk monitoring method disclosed in the above embodiment of the present application. Please refer to the corresponding parts of the chemical operation risk monitoring method provided in the above embodiment of the present application, and no further details will be given here.

[0132] An embodiment of the present application further provides a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned risk monitoring method for chemical operations.

[0133] The present application also provides an electronic device, the structure of which is shown in FIG. Figure 5 As shown, it specifically includes a memory 501 and one or more instructions 502, wherein the one or more instructions 502 are stored in the memory 501 and are configured to be executed by one or more processors 503 to perform the following operations:

[0134] When it is detected that the operation object is performing a chemical operation, the operation ticket data corresponding to the chemical operation and the operation site monitoring parameters are obtained;

[0135] Preprocessing the acquired operation ticket data and the operation site detection data to obtain time series data of the chemical operation, wherein the time series data includes key parameters of multiple time steps;

[0136] Processing the operation ticket data using a preset rule engine to obtain an initial risk score for the chemical operation;

[0137] Inputting the initial risk score and the time series data into a pre-trained time series prediction model to obtain a prediction result; the prediction result includes a change trend of key parameters of the chemical operation at the target time;

[0138] Obtaining a risk increment for the chemical operation according to the prediction result;

[0139] The chemical operation risk monitoring result is obtained according to the initial risk score, the prediction result and the dynamic risk increment.

[0140] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similarities between the various embodiments can be referred to in conjunction with each other. For device embodiments, since they are generally similar to method embodiments, their description is relatively simple, and for relevant details, reference can be made to the description of the method embodiments.

[0141] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0142] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0143] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present application or certain parts of the embodiments.

[0144] The above is a detailed introduction to a risk monitoring method for chemical operations provided by the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A chemical operation risk monitoring method, characterized in that: include: When it is detected that the operation object is performing a chemical operation, the operation ticket data corresponding to the chemical operation and the operation site monitoring parameters are obtained; Preprocessing the acquired operation ticket data and the operation site detection data to obtain time series data of the chemical operation, wherein the time series data includes key parameters of multiple time steps; Processing the operation ticket data using a preset rule engine to obtain an initial risk score for the chemical operation; Inputting the initial risk score and the time series data into a pre-trained time series prediction model to obtain a prediction result; the prediction result includes a change trend of key parameters of the chemical operation at the target time; Obtaining a risk increment for the chemical operation according to the prediction result; The chemical operation risk monitoring result is obtained according to the initial risk score, the prediction result and the dynamic risk increment.

2. The method according to claim 1, characterized in that The process of processing the operation ticket data using a preset rule engine to obtain an initial risk score of the chemical operation includes: Obtain each job record in the job ticket data; The rule engine is used to match the rules applicable to each of the operation records in the pre-built rule set to obtain the score of each of the operation records, and the risk scores of the various operation records are accumulated to obtain the initial risk score of the chemical operation.

3. The method according to claim 1, characterized in that The risk increment of the chemical operation is obtained according to the prediction result, including: Obtaining actual measurement results of the chemical operation at a target time; Calculating the sub-risk increment of each key parameter of the chemical operation according to the actual measurement result and the prediction result; The sub-risk increments of each of the key parameters are weighted and summed to calculate the risk increment of the chemical operation.

4. The method according to claim 1, characterized in that: The training process of the time series prediction model includes: Acquire an initial model and a training data set; the training data set includes a plurality of training samples; each of the training samples includes historical operation ticket data and operation site monitoring parameters for a preset time period; Using the training data set to train the initial model; When the initial model meets the preset training conditions, the initial model is used as the trained time series prediction model.

5. The method according to claim 1, characterized in that The risk monitoring result includes an operation risk score. After obtaining the chemical operation risk monitoring result according to the initial risk score, the prediction result and the dynamic risk increment, the following is further included: When the operation risk score is greater than a preset score threshold, an alarm message is output, and the alarm message is used to instruct to stop the chemical operation.

6. A chemical operation risk monitoring device, characterized in that: include: An acquisition unit, for acquiring operation ticket data and operation site monitoring parameters corresponding to the chemical operation when it is detected that the operation object performs the chemical operation; A preprocessing unit, used to preprocess the acquired operation ticket data and the operation site detection data to obtain time series data of the chemical operation, wherein the time series data includes key parameters of multiple time steps; A first execution unit, configured to process the operation ticket data using a preset rule engine to obtain an initial risk score of the chemical operation; A second execution unit is used to input the initial risk score and the time series data into a pre-trained time series prediction model to obtain a prediction result; the prediction result includes a change trend of key parameters of the chemical operation at a target time; A third execution unit, configured to obtain a risk increment of the chemical operation according to the prediction result; The fourth execution unit is used to obtain the chemical operation risk monitoring result according to the initial risk score, the prediction result and the dynamic risk increment.

7. The device according to claim 6, characterized in that The first execution unit includes: A first acquisition subunit, used to acquire each operation record in the operation ticket data; The matching subunit is used to use the rule engine to match the rules applicable to each of the operation records in the pre-built rule set, obtain the score of each of the operation records, accumulate the risk scores of each of the operation records, and obtain the initial risk score of the chemical operation.

8. The device according to claim 6, characterized in that The third execution unit includes: A second acquisition subunit is used to acquire the actual measurement result of the chemical operation at the target time; A first calculation subunit, configured to calculate a sub-risk increment of each of the key parameters of the chemical operation according to the actual measurement result and the prediction result; The second calculation subunit is used to perform weighted summation on the sub-risk increments of each of the key parameters to calculate the risk increment of the chemical operation.

9. A storage medium, characterized in that: The storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute a chemical operation risk monitoring method as described in any one of claims 1 to 5.

10. An electronic device, characterized in that: It comprises a memory and one or more instructions, wherein the one or more instructions are stored in the memory and are configured to be executed by one or more processors to perform a chemical operation risk monitoring method as described in any one of claims 1 to 5.

Images