Personnel positioning system and device applied to dangerous chemical safety production

Abstract

The invention provides a personnel positioning system and device applied to dangerous chemical safety production. The system comprises the following steps: collecting personnel activity data of a dangerous chemical safety production area to form a personnel activity database; according to the characteristics of a dangerous chemical safety production area, the area is divided, and meanwhile, influence factors of personnel positioning are identified for different parts of the area; predicting the positioning of the personnel in the dangerous chemical safety production area based on the influence factors of personnel positioning to obtain a personnel positioning reference position; and setting key influence factors of the same type of region based on the influence factors of personnel positioning, identifying the same type of historical personnel activity information based on the key influence factors, and then obtaining the same type of historical personnel activity reference position through data analysis. According to the invention, the prediction capability and adaptability of the system can be enhanced, and powerful technical support is provided for safety management of hazardous chemical enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of production safety monitoring, and more specifically, to a personnel positioning system and device applied to hazardous chemical production safety. Background Art

[0002] In the field of hazardous chemical production safety, the existing personnel positioning system technology has made significant progress. These systems use high-precision positioning technologies such as UWB and Bluetooth to achieve real-time positioning of personnel in the factory, behavior analysis, and illegal behavior alarms, effectively improving the level of safety management. These systems can not only monitor the location of personnel in real time, but also combine with intelligent inspections, one-button alarms and other functions, providing intelligent and refined means for the safety management of chemical companies.

[0003] However, in the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: Although the existing personnel positioning system has played an important role in improving the efficiency of safety management, there is still room for further optimization and improvement, especially in data processing, prediction algorithms, and linkage with other safety management systems. For example, the existing system may have limitations in positioning accuracy in complex environments, real-time data processing capabilities, and adaptability to different types of hazardous areas. In addition, the existing system may not be mature enough in terms of in-depth analysis and prediction of personnel behavior, and needs to be further combined with artificial intelligence and machine learning technologies to achieve more accurate and intelligent safety warning and management. Summary of the invention

[0004] The invention provides a personnel positioning system and device applied to hazardous chemical safety production.

[0005] In a first aspect of the present invention, a personnel positioning system for hazardous chemical production safety is provided, comprising:

[0006] Collecting personnel activity data in hazardous chemical production safety areas to form a personnel activity database, wherein the personnel activity data includes personnel identity information, activity trajectory and timestamp data;

[0007] According to the characteristics of hazardous chemical production safety areas, the areas are divided into regions, and the factors affecting the positioning of personnel are identified for different parts of the areas;

[0008] Based on the influencing factors of personnel positioning, the positioning of personnel in the hazardous chemical safety production area is predicted to obtain a reference position for personnel positioning;

[0009] The key influencing factors of the same type of area are set based on the influencing factors of the personnel positioning, the same type of historical personnel activity information is identified based on the key influencing factors, and then the same type of historical personnel activity reference positions are obtained through data analysis.

[0010] Furthermore, after determining the personnel positioning reference position, the method further includes:

[0011] Combined with the regional division, the predicted positions of personnel in different areas are compared with the reference positions of personnel, their deviations and impact ratios are determined, and areas with higher positioning accuracy requirements are adjusted first to control the deviations within a preset error range;

[0012] The personnel positioning system is used to predict the personnel positioning in different types of hazardous chemical safety production areas.

[0013] Furthermore, according to the characteristics of the hazardous chemical production safety area, the area is divided into regions, and the factors affecting the positioning of personnel are identified for different parts of the area, including:

[0014] Determine the characteristics of the area based on the layout diagram of the hazardous chemical production area;

[0015] The area is divided into a main production area, an auxiliary production area, a storage area and an office area according to the characteristics of the area; and the influencing factors of the personnel positioning in the main production area, the auxiliary production area, the storage area and the office area are identified, and the influencing factors of the personnel positioning include area area, equipment layout, personnel density, safety level, operation type, operation time and environmental conditions.

[0016] Furthermore, based on the influencing factors of personnel positioning, the positioning of personnel in the hazardous chemical production safety area is predicted, and the reference position of personnel positioning is obtained, including:

[0017] Predicting the positions of personnel in the main production area, auxiliary production area, storage area and office area respectively to obtain reference positions of personnel in different areas; and

[0018] The personnel positioning reference positions of the different areas are integrated to obtain the total personnel positioning reference position of the hazardous chemical safety production area.

[0019] Further, identifying the same type of historical personnel activity information based on the key influencing factors includes:

[0020] Based on the key influencing factors, all personnel activity data are searched, and a clustering algorithm is applied to find the number of clusters with the smallest error square sum J value and the corresponding initial cluster center;

[0021] After the initial cluster center is determined, the categories of personnel activity data and the centers of each category are finally determined according to the fuzzy clustering algorithm.

[0022] The key influencing factors of the main production area include operation type, operation time and equipment layout;

[0023] The key influencing factors of the auxiliary production area include personnel density and safety level;

[0024] The key factors affecting the storage area include the area size and environmental conditions;

[0025] The key influencing factors of the office area include personnel identity information and timestamp data.

[0026] Furthermore, the categories of personnel activity data and the centers of each category are finally determined according to the fuzzy clustering algorithm, further including:

[0027] The objective function of the fuzzy clustering algorithm is:

[0028] max{J(U,V)},

[0029] stJ=Jcom-Jsep,

[0030] Where c is the number of clusters, V = {v1, v2, ... vc} is a vector set in the feature space, vi represents the cluster prototype vector of the i-th class, i = 1, 2, ..., c, μik∈U, U is a c × n fuzzy matrix, and the fuzzy matrix satisfies the following conditions:

[0031]

[0032] Where n is the number of data. In the iterative process, the compactness Jcom and the inter-class separation Jsep of each type of data are calculated, and J=Jcom-Jsep is obtained. Then, the optimal number of clusters, cluster prototypes, and the type of personnel activity data are finally obtained by taking the maximum value of J.

[0033] Furthermore, the same type of historical personnel activity reference locations obtained through data analysis include:

[0034] Calculate the median, upper quartile, lower quartile, maximum value, minimum value, sample mean and sample variance of personnel activity data;

[0035] A box plot is used to remove outliers to perform an outlier analysis on the personnel activity data, wherein the outlier is less than the lower quartile QL minus 1.5 times the interquartile range QIQR, and greater than the upper quartile QU plus 1.5 times the interquartile range QIQR;

[0036] According to Chebyshev’s inequality principle, at least 80% of the statistics fall in the interval φ;

[0037] φ={x|μ-kσ≤x≤μ+kσ},

[0038] Wherein, μ is the mean value of the personnel activity data, σ is the standard deviation of the personnel activity data, and k is the interval coefficient;

[0039] Finally, the reasonable range of personnel positioning is μ-ki+1σ≤x≤μ+ki+1σ.

[0040] The same type of historical personnel activity reference position HRLS is calculated by the following formula:

[0041] HRLS={(μ-ki+1σ)+(μ+ki+1σ)} / 2.

[0042] Further, determining the personnel positioning prediction target according to the personnel positioning reference position and the historical personnel activity reference position includes:

[0043] The personnel positioning prediction target is determined by the following formula:

[0044] PPG=(HRLS+PRYC) / 2,

[0045] Among them, PPG is the predicted target of the person to be located, HRLS is the historical personnel activity reference position, and PRYC is the personnel positioning reference position constructed in combination with influencing factors.

[0046] Furthermore, based on the influencing factors of the personnel positioning, the positioning of the personnel in the hazardous chemical production safety area is predicted, and the personnel positioning reference position is obtained, including:

[0047] Based on the influencing factors of the personnel positioning, a neural network model based on genetic algorithm optimization is used to predict the positioning of the personnel in the hazardous chemical safety production area to obtain the personnel positioning reference position, wherein:

[0048] The neural network model maps the input vector to a high-dimensional feature space through nonlinear mapping, constructs an optimal classification hyperplane in the high-dimensional feature space, and the output of the neural network is a linear combination of intermediate nodes, wherein each intermediate node corresponds to a personnel positioning reference position.

[0049] In a second aspect of the present invention, a personnel positioning device for use in hazardous chemical production safety is provided, comprising:

[0050] A data acquisition module, used to collect personnel activity data in hazardous chemical production safety areas to form a personnel activity database, wherein the personnel activity data includes personnel identity information, activity trajectory and timestamp data;

[0051] An influencing factor identification module is used to divide the area into regions according to the characteristics of the hazardous chemical safety production area, and identify the influencing factors of personnel positioning for different parts of the area;

[0052] A positioning prediction module predicts the positioning of personnel in the hazardous chemical production safety area based on the influencing factors of the personnel positioning to obtain a reference position of the personnel positioning;

[0053] A historical position acquisition module is used to set key influencing factors of the same type of hazardous chemical safety production area based on the influencing factors of the personnel positioning, identify the same type of historical personnel activity information based on the key influencing factors, and then obtain the same type of historical personnel activity reference position through data analysis;

[0054] The prediction target acquisition module is used to determine the personnel positioning prediction target according to the personnel positioning reference position and the historical personnel activity reference position.

[0055] According to the above-mentioned embodiments of the present invention, at least the following beneficial effects are achieved: the system of the present invention can realize the real-time positioning and behavior analysis of personnel in hazardous chemical production safety areas. Through high-precision positioning technologies such as UWB, Bluetooth, etc., it can accurately track the location and activity trajectory of personnel, thereby timely warning of violations and potential risks, and effectively improving the level of safety management. Secondly, through intelligent data analysis and prediction algorithms, the system can predict the activities of personnel in specific areas, provide decision-making support for safety management, and also provide accurate personnel location information for emergency evacuation and rescue, thereby improving the efficiency and accuracy of emergency response. In addition, the personnel positioning system also has the function of linkage with other safety management systems, such as intelligent inspections, special operations management, etc., to achieve multi-system collaborative work and form a comprehensive safety monitoring network. The system also supports data exchange and interface docking, which is convenient for data sharing and integration with other information systems and government supervision platforms, and enhances the level of information and intelligence of safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0057] Figure 1 A schematic diagram of a flow chart of a personnel positioning system applied to hazardous chemical production safety provided by an embodiment of the present invention;

[0058] Figure 2 A schematic diagram of the structure of a personnel positioning device applied to hazardous chemical production safety provided by an embodiment of the present invention;

[0059] Figure 3 The schematic diagram schematically shows the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0061] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0062] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0063] Reference below Figure 1 , Figure 1 This is a flow chart of a personnel positioning system for hazardous chemical production safety provided by an embodiment of the present invention. Figure 1 As shown, a personnel positioning system 100 applied to hazardous chemical production safety includes:

[0064] Step 101, collecting personnel activity data in hazardous chemical production safety areas to form a personnel activity database, wherein the personnel activity data includes personnel identity information, activity trajectory and timestamp data;

[0065] Step 102, dividing the area into regions according to the characteristics of the hazardous chemical production safety area, and identifying factors affecting personnel positioning for different parts of the area;

[0066] Step 103, predicting the location of personnel in the hazardous chemical production safety area based on the influencing factors of personnel location, and obtaining a personnel location reference position;

[0067] Step 104 , setting key influencing factors of the same type of area based on the influencing factors of the personnel positioning, identifying the same type of historical personnel activity information based on the key influencing factors, and then obtaining the same type of historical personnel activity reference positions through data analysis.

[0068] It should be noted that the core of the system is to achieve accurate positioning and behavior monitoring of personnel in hazardous chemical production areas, and to form a personnel activity database by collecting and analyzing personnel activity data, which provides basic information for subsequent regional division and positioning prediction.

[0069] Specifically, personnel activity data includes but is not limited to basic personnel information such as work number, name, and specific behavior trajectory and timestamp data within a specific time. This data can be collected through various sensors, cameras or RFID tags, and transmitted to the central database through wireless networks for storage and processing. For example, timestamp data can be accurate to milliseconds, ensuring the real-time and accuracy of the data.

[0070] Preferably, the personnel activity database not only stores static data, but also has the function of dynamic update to adapt to the real-time changes in personnel behavior in hazardous chemical production safety areas. In addition, the system can also set different data collection frequencies and update cycles according to actual needs to balance the real-time nature of data and the efficiency of system resource use. Alternative solutions may include using cloud databases for data storage to improve the scalability and reliability of the system.

[0071] In some embodiments, after determining the personnel positioning reference position, the method further includes:

[0072] Combined with the regional division, the predicted positions of personnel in different areas are compared with the reference positions of personnel, their deviations and impact ratios are determined, and areas with higher positioning accuracy requirements are adjusted first to control the deviations within a preset error range;

[0073] The personnel positioning system is used to predict the personnel positioning in different types of hazardous chemical safety production areas.

[0074] It should be noted that the system further optimizes the accuracy of personnel positioning by comparing the deviations between the predicted positioning and the reference position in different areas, and making priority adjustments to areas with higher positioning accuracy requirements, thereby ensuring the high accuracy and reliability of the overall positioning system.

[0075] Specifically, the regional division can be based on the layout of the hazardous chemical production area and the actual functional requirements, and the area can be subdivided into the main production area, auxiliary production area, storage area and office area. The positioning accuracy requirements of each area may be different. For example, the main production area may require higher positioning accuracy due to its criticality and danger. The judgment of deviation and impact ratio can be achieved by setting an error threshold. When the deviation between the predicted position and the reference position exceeds this threshold, the system will automatically adjust the positioning algorithm or increase the sensor density in the area.

[0076] Preferably, the system can adopt an adaptive adjustment mechanism to dynamically adjust the parameters of the positioning prediction algorithm according to the deviation data monitored in real time, such as adjusting the weight of the neural network model or optimizing the initial clustering center of the clustering algorithm. In addition, the system can also combine the expert system to select the most appropriate positioning technology or adjust the parameter settings of the existing technology according to the safety level and operation characteristics of different areas to achieve the best positioning effect. Alternative solutions may include using different combinations of positioning technologies, such as using UWB technology in some areas and RFID technology in other areas to adapt to different environmental conditions and safety requirements.

[0077] In some embodiments, according to the characteristics of the hazardous chemical production safety area, the area is divided into regions, and the factors affecting the positioning of personnel are identified for different parts of the area, including:

[0078] Determine the characteristics of the area based on the layout diagram of the hazardous chemical production area;

[0079] Dividing the area into a main production area, an auxiliary production area, a storage area and an office area according to the characteristics of the area; and

[0080] The influencing factors of the personnel positioning are identified for the main production area, auxiliary production area, storage area and office area, and the influencing factors of the personnel positioning include area area, equipment layout, personnel density, safety level, operation type, operation time and environmental conditions.

[0081] It should be noted that the system provides a basis for accurate personnel positioning by making detailed regional divisions of hazardous chemical production areas and identifying key factors affecting personnel positioning.

[0082] Specifically, the area division can be carried out according to the layout diagram of the hazardous chemical production area, and the area can be divided into areas with different functions and safety requirements, such as the main production area, auxiliary production area, storage area and office area. The division of each area can be determined according to the actual geographical layout, process flow and safety regulations. The identification of influencing factors involves the analysis and recording of factors such as the size of each area, equipment layout, personnel density, safety level, operation type, operation time and environmental conditions.

[0083] Preferably, the system can use advanced data acquisition technologies, such as Internet of Things (IoT) devices and sensors, to automatically collect and monitor real-time data of the above-mentioned influencing factors. For example, infrared sensors can be used to monitor personnel density, temperature and humidity sensors can be used to monitor environmental conditions, and industrial cameras and image recognition technology can be used to analyze equipment layout and personnel behavior. In addition, the system can also be combined with artificial intelligence algorithms, such as machine learning and deep learning, to process and analyze the large amount of collected data, so as to more accurately predict personnel positioning.

[0084] More specifically, the system can set different data collection frequencies and analysis parameters according to the characteristics and security requirements of each area. For example, a higher frequency of data updates and a more sensitive anomaly detection threshold may be required in the main production area, while a lower data update frequency can be used in the office area. In addition, the system can dynamically adjust the positioning accuracy and complexity of the prediction model according to the security level of different areas to achieve optimal system performance and resource utilization. Alternative solutions may include using different data fusion technologies to combine multiple sensor data to improve positioning accuracy and robustness.

[0085] In some embodiments, the positioning of personnel in the hazardous chemical production safety area is predicted based on the influencing factors of personnel positioning, and the personnel positioning reference position is obtained, including:

[0086] Predicting the positions of personnel in the main production area, auxiliary production area, storage area and office area respectively to obtain reference positions of personnel in different areas; and

[0087] The personnel positioning reference positions of the different areas are integrated to obtain the total personnel positioning reference position of the hazardous chemical safety production area.

[0088] It should be noted that the system predicts the personnel positioning of the main production area, auxiliary production area, storage area and office area respectively, and then integrates the positioning reference positions of these areas to obtain the total personnel positioning reference position of the entire hazardous chemical safety production area.

[0089] Specifically, personnel location prediction can be achieved through a variety of technologies, such as using wireless communication technologies such as Wi-Fi, UWB, and RFID, combined with sensor networks and real-time location systems (RTLS), to track and locate personnel in each area in real time. The location data of each area will be collected and transmitted to the central processing unit, where they will be processed and analyzed to predict the location and behavior patterns of personnel. For example, the main production area may use a denser sensor layout to achieve higher-precision positioning.

[0090] Preferably, the system can use adaptive positioning algorithms to handle the specific conditions of different areas. For example, in the main production area, the impact of equipment layout and job type on positioning may be prioritized; while in the office area, more attention may be paid to personnel identity information and timestamp data. In addition, the system can use historical data and machine learning technology to continuously optimize the prediction model and improve positioning accuracy.

[0091] More specifically, the system can set different weight parameters to reflect the importance of different influencing factors. For example, the area of ​​the storage area may have a greater impact on positioning, so a higher weight can be set. At the same time, the system can use fuzzy logic or neural networks to deal with uncertainty and complexity in order to better adapt to environmental changes and predict personnel behavior. Alternatives may include the use of predictive models based on behavioral analysis, which can predict the future location and movement trajectory of personnel based on their historical behavior.

[0092] In some embodiments, identifying the same type of historical personnel activity information based on the key influencing factors includes:

[0093] Based on the key influencing factors, all personnel activity data are searched, and a clustering algorithm is applied to find the number of clusters with the smallest error square sum J value and the corresponding initial cluster center;

[0094] After the initial cluster center is determined, the categories of personnel activity data and the centers of each category are finally determined according to the fuzzy clustering algorithm.

[0095] The key influencing factors of the main production area include operation type, operation time and equipment layout;

[0096] The key influencing factors of the auxiliary production area include personnel density and safety level;

[0097] The key factors affecting the storage area include the area size and environmental conditions;

[0098] The key influencing factors of the office area include personnel identity information and timestamp data.

[0099] It should be noted that the system classifies personnel activity data by identifying key influencing factors and applying clustering algorithms, and then determines the center of each category, which is a key step in achieving accurate personnel location prediction.

[0100] Specifically, the key influencing factors may include, but are not limited to, the type of operation, operation time, equipment layout, personnel density, safety level, area and environmental conditions. These factors will be input into the clustering algorithm as features. The clustering algorithm can be implemented using K-means, DBSCAN or fuzzy C-means algorithm to determine the categories and centers of the data. For example, the key influencing factors of the main production area may be the type of operation and equipment layout, while the key influencing factors of the storage area may be the area and environmental conditions.

[0101] Preferably, the system can dynamically adjust the parameters of the clustering algorithm, such as the number of clusters, initial cluster centers, and learning rate, according to the weights and characteristics of the key influencing factors. In addition, the system can use the objective function of the fuzzy clustering algorithm to maximize the intra-class compactness and minimize the inter-class separation, thereby determining the optimal clustering result.

[0102] More specifically, the system can use methods such as cross-validation or grid search to determine the optimal number of clusters during the clustering process. At the same time, the system can also combine real-time monitoring data and historical activity records to update and adjust the clustering results in real time to adapt to changes in personnel behavior and production environment. Alternatives may include using deep learning-based clustering methods, such as autoencoders, to improve the performance and adaptability of clustering.

[0103] In some embodiments, finally determining the categories of personnel activity data and the centers of each category according to the fuzzy clustering algorithm further includes:

[0104] The objective function of the fuzzy clustering algorithm is:

[0105] max{J(U,V)},

[0106] stJ=Jcom-Jsep,

[0107] Where c is the number of clusters, V = {v1, v2, ... vc} is a vector set in the feature space, vi represents the cluster prototype vector of the i-th class, i = 1, 2, ..., c, μik∈U, U is a c × n fuzzy matrix, and the fuzzy matrix satisfies the following conditions:

[0108]

[0109] Where n is the number of data. In the iterative process, the compactness Jcom and the inter-class separation Jsep of each type of data are calculated, and J=Jcom-Jsep is obtained. Then, the optimal number of clusters, cluster prototypes, and the type of personnel activity data are finally obtained by taking the maximum value of J.

[0110] It should be noted that the system adopts a fuzzy clustering algorithm to determine the categories and category centers of personnel activity data. This method can better handle the uncertainty and ambiguity of data and improve the accuracy of positioning prediction.

[0111] Specifically, the fuzzy clustering algorithm is implemented by constructing the objective function max{J(U,V)}, where J is an indicator to measure the clustering effect, U is a fuzzy matrix, and V is a set of clustering prototype vectors. The algorithm calculates the compactness Jcom and the separation Jsep, and obtains J=J com -J sepTo evaluate the clustering effect, the goal is to maximize the value of J. The parameter c represents the number of clusters, and n is the number of data. The element μ in the fuzzy matrix U is ik Satisfy the condition μ ik +μ jk ≤1, for all i≠j and k=1,2,…,n.

[0112] Preferably, the system can dynamically adjust the number of clusters c and the parameters of the fuzzy matrix U during the iteration process to adapt to the changing data distribution. In addition, the system can use various heuristic or meta-heuristic algorithms to optimize the determination process of the cluster prototype vector V, such as genetic algorithm, particle swarm optimization or simulated annealing algorithm.

[0113] More specifically, the system can set an initial range of cluster numbers, evaluate the J values ​​under different cluster numbers in each iteration, and select c that maximizes the J value as the final number of clusters. At the same time, the system can introduce a convergence criterion, and stop the iteration when the change in the J value in several consecutive iterations is less than a preset threshold, so as to improve the efficiency of the algorithm. Alternatives may include using other fuzzy clustering algorithms, such as the Gath-Geva algorithm or the Krishnapuram-Keller algorithm, which may perform better when processing specific types of data.

[0114] In some embodiments, obtaining the same type of historical personnel activity reference locations through data analysis includes:

[0115] Calculate the median, upper quartile, lower quartile, maximum value, minimum value, sample mean and sample variance of personnel activity data;

[0116] A box plot is used to remove outliers to perform an outlier analysis on the personnel activity data, wherein the outlier is less than the lower quartile QL minus 1.5 times the interquartile range QIQR, and greater than the upper quartile QU plus 1.5 times the interquartile range QIQR;

[0117] According to Chebyshev’s inequality principle, at least 80% of the statistics fall in the interval φ;

[0118] φ={x|μ-kσ≤x≤μ+kσ},

[0119] Wherein, μ is the mean value of the personnel activity data, σ is the standard deviation of the personnel activity data, and k is the interval coefficient;

[0120] Finally, the reasonable range of personnel positioning is μ-ki+1σ≤x≤μ+ki+1σ.

[0121] The same type of historical personnel activity reference position HRLS is calculated by the following formula:

[0122] HRLS={(μ-ki+1σ)+(μ+ki+1σ)} / 2.

[0123] It should be noted that the system obtains the reference positions of historical personnel activities of the same type through data analysis, which involves statistical analysis and outlier processing of personnel activity data to ensure the accuracy and reliability of positioning prediction.

[0124] Specifically, data analysis includes calculating statistics such as the median, upper quartile, lower quartile, maximum, minimum, sample mean, and sample variance of personnel activity data. These statistics provide a basis for understanding the distribution and characteristics of the data. Outlier analysis is performed through box plots, and abnormal data points that are less than the lower quartile minus 1.5 times the interquartile range or greater than the upper quartile plus 1.5 times the interquartile range are eliminated. In addition, Chebyshev's inequality is used to estimate the distribution interval of the data, where at least 80% of the data fall within the interval of the mean plus or minus k times the standard deviation, where k is the interval coefficient.

[0125] Preferably, the system can select a suitable k value according to the actual application scenario and data characteristics to determine a reasonable data distribution interval. In addition, the system can use an automated algorithm to identify and remove outliers, reduce manual intervention, and improve the efficiency and accuracy of data processing.

[0126] More specifically, the system can introduce adaptive algorithms in the data analysis process to dynamically adjust the calculation method of statistics and the criteria for determining outliers according to the real-time changes in the data. For example, the system can use moving average or exponential weighted average to calculate the sample mean to more smoothly reflect the changing trend of the data. Alternatives may include using other statistical methods, such as Gaussian mixture models or support vector machines, to identify and process outliers.

[0127] In some embodiments, determining a personnel location prediction target according to the personnel location reference position and the historical personnel activity reference position includes:

[0128] The personnel positioning prediction target is determined by the following formula:

[0129] PPG=(HRLS+PRYC) / 2,

[0130] Among them, PPG is the predicted target of the person to be located, HRLS is the historical personnel activity reference position, and PRYC is the personnel positioning reference position constructed in combination with influencing factors.

[0131] It should be noted that the system determines the personnel positioning prediction target by combining the personnel positioning reference position and the historical personnel activity reference position. This process aims to improve the accuracy and practicality of positioning prediction.

[0132] Specifically, the personnel location prediction target is obtained by calculating the average of the historical personnel activity reference position (HRLS) and the personnel location reference position (PRYC). The historical personnel activity reference position is obtained based on data analysis, for example, the median or average value can be determined by statistical methods. The personnel location reference position is the current personnel location prediction based on real-time monitoring data and prediction models. Parameter settings may include selecting different mathematical formulas to calculate the average, such as simple arithmetic mean or weighted average to reflect the importance of different data points.

[0133] Preferably, the system can use more complex algorithms to determine the prediction target, such as exponential smoothing or adaptive filtering techniques that take time factors into account. In addition, the system can also introduce confidence intervals or prediction intervals to assess the uncertainty of the prediction and the possible error range.

[0134] More specifically, the system can set up a real-time update mechanism to dynamically adjust the prediction target to ensure that it reflects the latest personnel activities and environmental changes. For example, the system can use a Kalman filter to fuse real-time data and historical data to obtain more accurate prediction results. Alternatives include using neural networks or deep learning models that can learn from large amounts of historical data and predict personnel behavior patterns.

[0135] In some embodiments, the positioning of personnel in the hazardous chemical production safety area is predicted based on the influencing factors of the personnel positioning, and obtaining the personnel positioning reference position includes:

[0136] Based on the influencing factors of the personnel positioning, a neural network model based on genetic algorithm optimization is used to predict the positioning of the personnel in the hazardous chemical safety production area to obtain the personnel positioning reference position, wherein:

[0137] The neural network model maps the input vector to a high-dimensional feature space through nonlinear mapping, constructs an optimal classification hyperplane in the high-dimensional feature space, and the output of the neural network is a linear combination of intermediate nodes, wherein each intermediate node corresponds to a personnel positioning reference position.

[0138] It should be noted that the genetic algorithm is a search algorithm that simulates the principles of natural selection and genetics and is used to optimize the weights and bias parameters of a neural network. The neural network model can be a multi-layer perceptron, a convolutional neural network, or a recurrent neural network, etc. The specific model to be selected depends on the characteristics and complexity of the personnel positioning data. Nonlinear mapping is a mathematical function used in a neural network to process input data and map it to a high-dimensional feature space. The optimal classification hyperplane is a concept in a support vector machine that is used to find the best decision boundary in a high-dimensional space.

[0139] Preferably, the system can set the parameters of the genetic algorithm, such as population size, crossover rate, mutation rate and number of iterations, to ensure the convergence and optimization effect of the algorithm. At the same time, the parameters of the neural network model, such as the number of layers, the number of neurons in each layer, the type of activation function, etc., also need to be adjusted according to the actual application.

[0140] More specifically, the system can use an adaptive genetic algorithm to dynamically adjust the parameters of the genetic algorithm based on feedback during the optimization process to improve optimization efficiency. In the neural network model, regularization techniques such as L1 or L2 regularization can be used to prevent overfitting and improve the generalization ability of the model. Alternatives may include using other types of optimization algorithms, such as particle swarm optimization or gradient descent, or using ensemble learning methods to combine the prediction results of multiple neural network models to improve the accuracy of positioning predictions.

[0141] The above-mentioned embodiments of the present invention have the following beneficial effects: The personnel positioning system of the present invention can significantly improve the accuracy and response speed of personnel positioning in hazardous chemical production safety areas by comprehensively applying advanced technologies such as data collection, regional division, influencing factor analysis, prediction model and historical data analysis. The system can not only monitor and analyze personnel activities in real time and predict their behavior patterns, but also respond quickly in emergency situations, provide a scientific basis for safety management decisions, thereby effectively reducing the risk of safety accidents and ensuring the safety of personnel and production facilities. In addition, the system can enhance the predictive ability and adaptability of personnel behavior in complex industrial environments through intelligent algorithm optimization and data analysis. The design of the system takes into account the special needs of different hazardous chemical areas, and through refined management, the practicality and flexibility of the positioning system can be improved. At the same time, the system's in-depth mining and application of historical data can further improve the accuracy of predictions, provide strong data support and decision-making assistance for the safety management of chemical companies, and help build a safer and more reliable production environment.

[0142] like Figure 2 As shown, in some embodiments, a personnel positioning device 200 applied to hazardous chemical production safety, the device 200 includes:

[0143] A data acquisition module, used to collect personnel activity data in hazardous chemical production safety areas to form a personnel activity database, wherein the personnel activity data includes personnel identity information, activity trajectory and timestamp data;

[0144] An influencing factor identification module is used to divide the area into regions according to the characteristics of the hazardous chemical safety production area, and identify the influencing factors of personnel positioning for different parts of the area;

[0145] A positioning prediction module predicts the positioning of personnel in the hazardous chemical production safety area based on the influencing factors of the personnel positioning to obtain a reference position of the personnel positioning;

[0146] A historical position acquisition module is used to set key influencing factors of the same type of hazardous chemical safety production area based on the influencing factors of the personnel positioning, identify the same type of historical personnel activity information based on the key influencing factors, and then obtain the same type of historical personnel activity reference position through data analysis;

[0147] The prediction target acquisition module is used to determine the personnel positioning prediction target according to the personnel positioning reference position and the historical personnel activity reference position.

[0148] It can be understood that the modules recorded in the personnel positioning device 200 for hazardous chemical production safety are similar to those in the reference Figure 1 Therefore, the steps, features and beneficial effects described above for the personnel positioning system for hazardous chemical safety production are also applicable to the personnel positioning device 200 for hazardous chemical safety production and the modules contained therein, and will not be repeated here.

[0149] Reference below Figure 3 , which shows a schematic diagram of a structure 300 of an electronic device suitable for implementing some embodiments of the present invention. The electronic devices in some embodiments of the present invention may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0150] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0151] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0152] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0153] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention to form a technical solution.

Claims

1. A personnel positioning system applied to hazardous chemical production safety, characterized in that: The system performs the following steps: Collecting personnel activity data in hazardous chemical production safety areas to form a personnel activity database, wherein the personnel activity data includes personnel identity information, activity trajectory and timestamp data; According to the characteristics of hazardous chemical production safety areas, the areas are divided into regions, and the factors affecting the positioning of personnel are identified for different parts of the areas; Based on the influencing factors of personnel positioning, the positioning of personnel in the hazardous chemical safety production area is predicted to obtain a reference position for personnel positioning; The key influencing factors of the same type of area are set based on the influencing factors of the personnel positioning, the same type of historical personnel activity information is identified based on the key influencing factors, and then the same type of historical personnel activity reference positions are obtained through data analysis.

2. The system according to claim 1, characterized in that After determining the reference position of the personnel, the method further includes: Combined with the regional division, the predicted positions of personnel in different areas are compared with the reference positions of personnel, their deviations and impact ratios are determined, and areas with higher positioning accuracy requirements are adjusted first to control the deviations within a preset error range; The personnel positioning system is used to predict the personnel positioning in different types of hazardous chemical safety production areas.

3. The system according to claim 1, characterized in that According to the characteristics of hazardous chemical production safety areas, the areas are divided into regions, and the factors affecting personnel positioning are identified for different parts of the areas, including: Determine the characteristics of the area based on the layout diagram of the hazardous chemical production area; Dividing the area into a main production area, an auxiliary production area, a storage area and an office area according to the characteristics of the area; and The influencing factors of the personnel positioning are identified for the main production area, auxiliary production area, storage area and office area, and the influencing factors of the personnel positioning include area area, equipment layout, personnel density, safety level, operation type, operation time and environmental conditions.

4. The system according to claim 3, characterized in that Based on the influencing factors of personnel positioning, the positioning of personnel in the hazardous chemical safety production area is predicted, and the reference positions of personnel positioning are obtained, including: Predicting the positions of personnel in the main production area, auxiliary production area, storage area and office area respectively to obtain reference positions of personnel in different areas; and The personnel positioning reference positions of the different areas are integrated to obtain the total personnel positioning reference position of the hazardous chemical safety production area.

5. The system according to claim 3, characterized in that Identifying the same type of historical personnel activity information based on the key influencing factors includes: Based on the key influencing factors, all personnel activity data are searched, and a clustering algorithm is applied to find the number of clusters with the smallest error square sum J value and the corresponding initial cluster center; After the initial cluster center is determined, the categories of personnel activity data and the centers of each category are finally determined according to the fuzzy clustering algorithm. The key influencing factors of the main production area include operation type, operation time and equipment layout; The key influencing factors of the auxiliary production area include personnel density and safety level; The key factors affecting the storage area include the area size and environmental conditions; The key influencing factors of the office area include personnel identity information and timestamp data.

6. The system according to claim 5, characterized in that The categories of personnel activity data and the centers of each category are finally determined according to the fuzzy clustering algorithm, which further includes: The objective function of the fuzzy clustering algorithm is: max{J(U,V)}, stJ=Jcom-Jsep, Where c is the number of clusters, V = {v1, v2, ... vc} is a vector set in the feature space, vi represents the cluster prototype vector of the i-th class, i = 1, 2, ..., c, μik∈U, U is a c × n fuzzy matrix, and the fuzzy matrix satisfies the following conditions: Where n is the number of data. In the iterative process, the compactness Jcom and the inter-class separation Jsep of each type of data are calculated, and J=Jcom-Jsep is obtained. Then, the optimal number of clusters, cluster prototypes, and the type of personnel activity data are finally obtained by taking the maximum value of J.

7. The system according to claim 1, characterized in that The same type of historical personnel activity reference locations obtained through data analysis include: Calculate the median, upper quartile, lower quartile, maximum value, minimum value, sample mean and sample variance of personnel activity data; A box plot is used to remove outliers to perform an outlier analysis on the personnel activity data, wherein the outlier is less than the lower quartile QL minus 1.5 times the interquartile range QIQR, and greater than the upper quartile QU plus 1.5 times the interquartile range QIQR; According to Chebyshev’s inequality principle, at least 80% of the statistics fall in the interval φ; φ={x|μ-kσ≤x≤μ+kσ}, Wherein, μ is the mean value of the personnel activity data, σ is the standard deviation of the personnel activity data, and k is the interval coefficient; Finally, the reasonable range of personnel positioning is μ-ki+1σ≤x≤μ+ki+1σ. The same type of historical personnel activity reference position HRLS is calculated by the following formula: HRLS={(μ-ki+1σ)+(μ+ki+1σ)} / 2.

8. The method according to claim 7, characterized in that: Determining a personnel positioning prediction target according to the personnel positioning reference position and the historical personnel activity reference position includes: The personnel positioning prediction target is determined by the following formula: PPG=(HRLS+PRYC) / 2, Among them, PPG is the predicted target of the person to be located, HRLS is the historical personnel activity reference position, and PRYC is the personnel positioning reference position constructed in combination with influencing factors.

9. The method according to claim 1, characterized in that: Based on the influencing factors of personnel positioning, the positioning of personnel in the hazardous chemical safety production area is predicted, and the reference position of personnel positioning is obtained, including: Based on the influencing factors of the personnel positioning, a neural network model based on genetic algorithm optimization is used to predict the positioning of the personnel in the hazardous chemical safety production area to obtain the personnel positioning reference position, wherein: The neural network model maps the input vector to a high-dimensional feature space through nonlinear mapping, constructs an optimal classification hyperplane in the high-dimensional feature space, and the output of the neural network is a linear combination of intermediate nodes, wherein each intermediate node corresponds to a personnel positioning reference position.

10. A personnel positioning device for hazardous chemical production safety, applied to a personnel positioning system for hazardous chemical production safety as claimed in claims 1-9, characterized in that: include: A data acquisition module, used to collect personnel activity data in hazardous chemical production safety areas to form a personnel activity database, wherein the personnel activity data includes personnel identity information, activity trajectory and timestamp data; An influencing factor identification module is used to divide the area into regions according to the characteristics of the hazardous chemical safety production area, and identify the influencing factors of personnel positioning for different parts of the area; A positioning prediction module predicts the positioning of personnel in the hazardous chemical production safety area based on the influencing factors of the personnel positioning to obtain a reference position of the personnel positioning; A historical position acquisition module is used to set key influencing factors of the same type of hazardous chemical safety production area based on the influencing factors of the personnel positioning, identify the same type of historical personnel activity information based on the key influencing factors, and then obtain the same type of historical personnel activity reference position through data analysis; The prediction target acquisition module is used to determine the personnel positioning prediction target according to the personnel positioning reference position and the historical personnel activity reference position.

Images