A safety production management system based on big data analysis

Abstract

A production safety management system based on big data analysis relates to the technical field of production management. A digital twin model is constructed to compare environmental parameters and equipment operation status parameters with production safety standards to determine whether there are production safety problems, obtain a number of production sub-processes and their delay sub-coefficients under different environmental parameters and equipment operation status parameters, obtain production efficiency and construct a production efficiency curve, obtain weight values ​​of each production sub-process according to the production efficiency curve, obtain a delay coefficient in combination with the delay sub-coefficient, obtain an actual delay coefficient in combination with the actual delay sub-coefficient and the weight value, and input it into a preset production prediction model to obtain predicted production efficiency, and adjust the speed of each production sub-process according to the predicted production efficiency. This is conducive to keeping the actual production efficiency within a stable floating range when environmental parameters and equipment operation status parameters are constantly changing.

Description

Technical Field

[0001] The present invention relates to the technical field of production management, and in particular to a safe production management system based on big data analysis. Background Art

[0002] Safety production management is an indispensable and important direction in modern industrial production. It integrates a variety of advanced technologies and methods, such as sensor technology, real-time database, big data analysis, etc., to achieve comprehensive perception, monitoring, early warning, disposal and evaluation of industrial safety production, and then gradually improve the production efficiency of industrial production on the basis of safety production;

[0003] Existing technical solutions often fail to effectively combine safety monitoring and efficiency optimization. They only stay at the level of monitoring various environmental parameters and equipment operating status parameters, but fail to deeply analyze the impact of these parameters on production efficiency. In addition, the existing technology often analyzes the entire production process as a whole, ignoring the fact that different production equipment is affected differently by environmental parameters and equipment operating status parameters. In view of the shortcomings of the existing technology, the present invention provides a safe production management system based on big data analysis. Summary of the invention

[0004] The purpose of the present invention is to provide a safe production management system based on big data analysis.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A production safety management system based on big data analysis, comprising the following modules:

[0006] The data acquisition module is used to collect environmental parameters, equipment operating status parameters, and actual production parameters, and build corresponding digital twin models;

[0007] The safety monitoring module is used to set the safety production standards and compare the environmental parameters and equipment operation status parameters with the safety production standards to determine whether there are any safety production problems;

[0008] A process division module is used to divide the production process to obtain several production sub-processes, and obtain the delay sub-coefficient of each production sub-process under different environmental parameters and equipment operation status parameters;

[0009] The efficiency evaluation module is used to set the evaluation cycle, obtain the production efficiency under different environmental parameters and equipment operation status parameters, and construct the production efficiency curve. According to the production efficiency curve, the weight value of each production sub-process is obtained, and the corresponding delay coefficient is obtained in combination with the delay sub-coefficient;

[0010] The production prediction module is used to obtain the actual delay sub-coefficient, combine the weight value to obtain the actual delay coefficient, and input it into the preset production prediction model to obtain the predicted production efficiency, and adjust the speed of each production sub-process according to the predicted production efficiency.

[0011] Furthermore, the process of collecting environmental parameters, equipment operating status parameters, and actual production parameters and building corresponding digital twin models includes:

[0012] The environmental parameters include the workshop temperature, workshop humidity, and light intensity of the production workshop; the equipment operation status parameters include the equipment temperature, vibration amplitude, and equipment energy consumption of the production equipment; and the actual production parameters include the process parameters, production process, and quality standards of the production products;

[0013] The construction process of the digital twin model includes: using CAD software to construct a geometric model of the production workshop and production equipment, constructing a physical model of the production equipment based on the geometric model, and integrating the geometric model and the physical model to obtain the corresponding digital twin model.

[0014] Furthermore, the process of setting production safety standards and comparing environmental parameters and equipment operation status parameters with the production safety standards to determine whether there are production safety problems includes:

[0015] The safety production standards include workshop temperature standards, workshop humidity standards, light intensity standards, equipment temperature standards, vibration amplitude standards, and equipment energy consumption standards;

[0016] The relevant parameters in the environmental parameters and equipment operating status parameters are compared with their corresponding production safety standards. If the relevant parameters are not within the range of the production safety standards, it is judged that there is a production safety problem, and corresponding abnormal signals are generated according to the relevant parameters for feedback. When various abnormal signals appear, the production equipment is controlled to sound an alarm.

[0017] Furthermore, the production process is divided to obtain a plurality of production sub-processes, and the process of obtaining the delay sub-coefficient of each production sub-process under different environmental parameters and equipment operation status parameters includes:

[0018] The production process refers to the entire process of producing products from raw material processing to finished products. According to the production situation of the products in the production process, the production process is divided into several production sub-processes, including the first sub-process, the second sub-process, the third sub-process, the fourth sub-process, and the fifth sub-process;

[0019] Obtain the theoretical processing time of each production sub-process. In the digital twin model, adjust the relevant parameters in the environmental parameters and equipment operation status parameters respectively to obtain the simulated processing time of each production sub-process under different environmental parameters and equipment operation status parameters.

[0020] According to the theoretical processing time and simulated processing time of each production sub-process, the delay sub-coefficients of each production sub-process under different environmental parameters and equipment operation status parameters are obtained, including the first sub-coefficient, the second sub-coefficient, the third sub-coefficient, the fourth sub-coefficient and the fifth sub-coefficient.

[0021] Furthermore, the process of setting an evaluation cycle, obtaining production efficiency under different environmental parameters and equipment operating status parameters, and constructing a production efficiency curve includes:

[0022] The production efficiency refers to the number of products produced by the production equipment in a single evaluation cycle. In the digital twin model, a set of environmental parameters and equipment operating status parameters are kept unchanged in a single evaluation cycle to obtain the production efficiency and its delay sub-coefficient in the evaluation cycle;

[0023] The environmental parameters and equipment operation status parameters are adjusted to obtain the production efficiency and delay sub-coefficients in different evaluation cycles, the obtained evaluation cycles are numbered, and a production efficiency curve is constructed with the horizontal axis being the evaluation cycle and the vertical axis being the corresponding production efficiency.

[0024] Furthermore, the process of obtaining the weight value of each production sub-process according to the production efficiency curve and obtaining the corresponding delay coefficient in combination with the delay sub-coefficient includes:

[0025] The production efficiency curve is regarded as a scatter plot, and its corresponding regression line is taken as the production efficiency line. The delay sub-coefficients under the environmental parameters and equipment operation status parameters corresponding to different evaluation cycles are added to the production efficiency line.

[0026] The shortest distance between the coordinate point of the delay sub-coefficient in the same evaluation period and the production efficiency straight line is used as the weight value of the delay sub-coefficient in the evaluation period, including a first weight value, a second weight value, a third weight value, a fourth weight value, and a fifth weight value;

[0027] According to the delay sub-coefficients in different evaluation periods and their corresponding weight values, the delay coefficient in each evaluation period is obtained, and the obtained delay coefficient is bound to the environmental parameters and equipment operation status parameters corresponding to its evaluation period.

[0028] Further, the process of obtaining the actual delay sub-coefficient, combining the weight value to obtain the actual delay coefficient, and inputting it into a preset production prediction model to obtain the predicted production efficiency includes:

[0029] In the actual production process, the actual delay sub-coefficient of each production sub-process is monitored in real time, the current weight value of each production sub-process is obtained according to the current environmental parameters and equipment operation status parameters, and the current actual delay coefficient is obtained according to the actual delay sub-coefficient and its corresponding weight value;

[0030] The preset process of the production prediction model is as follows: generating a production prediction set according to different delay coefficients and their corresponding production efficiencies, and dividing the production prediction set into a training set and a test set;

[0031] Construct a convolutional neural network, use the delay coefficient in the training set as input data of the convolutional neural network, use the corresponding production efficiency in the training set as output data of the convolutional neural network, and train the convolutional neural network to obtain an initial convolutional neural network;

[0032] The test set is used to verify the model of the initial convolutional neural network, and the output of the initial convolutional neural network that is less than or equal to the preset test error threshold is used as the corresponding production prediction model.

[0033] Furthermore, the process of adjusting the speed of each production sub-process according to the predicted production efficiency includes:

[0034] Set the expected production efficiency, use the production prediction model to obtain the predicted production efficiency of the production equipment in real time, compare the predicted production efficiency with the expected production efficiency, and if the predicted production efficiency is lower than the expected production efficiency, adjust the speed of each production sub-process. The speed adjustment refers to adjusting the processing speed of each production sub-process until the corresponding actual delay sub-coefficient returns to zero.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] 1. The present invention constructs a digital twin model and divides the entire production process into several production sub-processes. The digital twin model can be used to simulate the production efficiency and equipment status of each production sub-process under different environmental parameters and equipment operation status parameters, which is conducive to obtaining the delay sub-coefficient of each production sub-process and can accurately reflect the influence of different environmental parameters and equipment operation status parameters on the production sub-process;

[0037] 2. The present invention obtains the production efficiency under ideal conditions, constructs a production efficiency curve and a production efficiency line, and can obtain the correlation between different delay sub-coefficients and production efficiency, and use it as a weight value to obtain the total delay coefficient. The actual delay coefficient can be obtained based on the current actual delay sub-coefficient and the weight value under the corresponding environmental parameters and equipment operating status parameters. The subsequent predicted production efficiency can be obtained by constructing a production prediction model, and the speed of each production sub-process can be adjusted according to the predicted production efficiency. This is beneficial to keeping the actual production efficiency within a stable floating range when the environmental parameters and equipment operating status parameters are constantly changing. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0039] like Figure 1 As shown, a safety production management system based on big data analysis includes the following modules:

[0040] The data acquisition module is used to collect environmental parameters, equipment operating status parameters, and actual production parameters, and build corresponding digital twin models;

[0041] The safety monitoring module is used to set the safety production standards and compare the environmental parameters and equipment operation status parameters with the safety production standards to determine whether there are any safety production problems;

[0042] A process division module is used to divide the production process to obtain several production sub-processes, and obtain the delay sub-coefficient of each production sub-process under different environmental parameters and equipment operation status parameters;

[0043] The efficiency evaluation module is used to set the evaluation cycle, obtain the production efficiency under different environmental parameters and equipment operation status parameters, and construct the production efficiency curve. According to the production efficiency curve, the weight value of each production sub-process is obtained, and the corresponding delay coefficient is obtained in combination with the delay sub-coefficient;

[0044] The production prediction module is used to obtain the actual delay sub-coefficient, combine the weight value to obtain the actual delay coefficient, and input it into the preset production prediction model to obtain the predicted production efficiency, and adjust the speed of each production sub-process according to the predicted production efficiency.

[0045] It should be further explained that, in the specific implementation process, the environmental parameters, equipment operation status parameters, and actual production parameters are collected respectively, and the process of building the corresponding digital twin model includes:

[0046] The environmental parameters refer to the workshop temperature, workshop humidity, light intensity, etc. in the production workshop; the equipment operation status parameters refer to the equipment temperature, vibration amplitude, equipment energy consumption, etc. of the production equipment in the production workshop; the actual production parameters refer to the process parameters, production process, quality standards, etc. of the products produced by the production equipment;

[0047] Use CAD software to build geometric models of production workshops and production equipment, which can reflect the actual appearance and size of the production workshops and production equipment. On the basis of the geometric model, build a physical model of the production equipment based on physical laws and principles, which can simulate the operation process, energy consumption value, vibration amplitude and other physical characteristics of the production equipment;

[0048] The constructed geometric model and physical model are integrated to obtain the corresponding digital twin model, and the digital twin model is simulated and run on the simulation platform to simulate the production process of the production workshop and the operating status of the production equipment. By adjusting the model parameters and input data, the production efficiency and equipment status under different production conditions can be obtained.

[0049] It should be further explained that, in the specific implementation process, the process of setting production safety standards and comparing environmental parameters and equipment operating status parameters with the production safety standards to determine whether there are production safety problems includes:

[0050] Set safety production standards for production workshops and production equipment, including workshop temperature standards, workshop humidity standards, light intensity standards, equipment temperature standards, vibration amplitude standards, equipment energy consumption standards, etc.;

[0051] The safety production standard is used to indicate that the production workshop and production equipment can produce normally within this range, and the relevant parameters in the collected environmental parameters and equipment operation status parameters are compared with their corresponding safety production standards respectively;

[0052] If the relevant parameters are within (or equal to) the range of the safety production standards, it is judged that there is no safety production problem. If the relevant parameters are not within the range of the safety production standards, it is judged that there is a safety production problem, and the corresponding abnormal signal is generated according to the relevant parameters for feedback;

[0053] For example, the workshop temperature is compared with the workshop temperature standard. When the workshop temperature is not within the workshop temperature standard, a workshop temperature abnormality signal is generated. The equipment temperature is compared with the equipment temperature standard. When the equipment temperature is not within the equipment temperature standard, an equipment temperature abnormality signal is generated.

[0054] The abnormal signals include abnormal workshop temperature signal, abnormal workshop humidity signal, abnormal light intensity signal, abnormal equipment temperature signal, abnormal vibration amplitude signal, abnormal equipment energy consumption signal, etc. When any abnormal signal appears, the production equipment is controlled to sound an alarm.

[0055] It should be further explained that, in the specific implementation process, the production process is divided to obtain a number of production sub-processes, and the process of obtaining the delay sub-coefficient of each production sub-process under different environmental parameters and equipment operation status parameters includes:

[0056] The production process refers to the entire process of manufacturing products from raw materials to finished products. The obtained production process is divided into several production sub-processes according to the production situation of the products in the production process. The production situation can be different production equipment or production nodes with obvious differences in the same production equipment, which is determined by the staff;

[0057] In an embodiment of the present invention, each divided production sub-process is marked as a first sub-process, a second sub-process, a third sub-process, a fourth sub-process, and a fifth sub-process, and a theoretical processing time of each production sub-process is obtained. The theoretical processing time refers to the time required for a production sub-process to complete its corresponding production content under ideal conditions;

[0058] In the digital twin model, relevant parameters in the environmental parameters and the equipment operating status parameters are adjusted respectively to obtain the simulated processing time of each production sub-process under different environmental parameters and equipment operating status parameters. The simulated processing time is used to reflect the processing time of each production sub-process after being affected by different environmental parameters and equipment operating status parameters.

[0059] Take any production sub-process as an example and mark its theoretical processing time as S L , and mark its simulated processing time as S M , obtain the delay sub-coefficient Y of the production sub-process;

[0060]

[0061] Obtain the delay sub-coefficients of each production sub-process under different environmental parameters and equipment operation status parameters, including a first sub-coefficient, a second sub-coefficient, a third sub-coefficient, a fourth sub-coefficient, and a fifth sub-coefficient.

[0062] It should be further explained that, in the specific implementation process, the process of setting the evaluation cycle, obtaining the production efficiency under different environmental parameters and equipment operating status parameters, and constructing the production efficiency curve includes:

[0063] The production efficiency refers to the number of products produced by the production equipment in a single evaluation cycle. In the digital twin model, a set of environmental parameters and equipment operating status parameters are kept unchanged in a single evaluation cycle to obtain the production efficiency and its various delay sub-coefficients in the evaluation cycle;

[0064] The environmental parameters and equipment operation status parameters are adjusted to obtain the production efficiency and delay sub-coefficients in different evaluation cycles. The environmental parameters and equipment operation status parameters corresponding to each evaluation cycle are not exactly the same. The obtained evaluation cycles are numbered and recorded as i, where i=1, 2, ..., n, and n is the total number of evaluation cycles;

[0065] The horizontal axis is constructed as the evaluation cycle, i.e., evaluation cycle 1, evaluation cycle 2, evaluation cycle 3, ..., and the vertical axis is a two-dimensional curve graph of the production efficiency corresponding to each evaluation cycle, i.e., the production efficiency curve. The production efficiency curve includes the production efficiency of different evaluation cycles, and different evaluation cycles correspond to different environmental parameters and equipment operation status parameters.

[0066] It should be further explained that, in the specific implementation process, the weight value of each production sub-process is obtained according to the production efficiency curve, and the process of obtaining the corresponding delay coefficient in combination with the delay sub-coefficient includes:

[0067] The production efficiency curve is regarded as a scatter plot, and its corresponding regression line is constructed, which is recorded as the production efficiency line. On the basis of the production efficiency line, the delay sub-coefficients under the environmental parameters and equipment operation status parameters corresponding to different evaluation periods are added to the production efficiency line. The horizontal axis is still the evaluation period, and the vertical axis is the delay sub-coefficients of each item.

[0068] The shortest distance between the coordinate point of the delay sub-coefficient in the same evaluation period and the production efficiency straight line is used as the weight value of the delay sub-coefficient in the evaluation period, including a first weight value, a second weight value, a third weight value, a fourth weight value, and a fifth weight value;

[0069] Taking any evaluation period as an example, the first sub-coefficient, the second sub-coefficient, the third sub-coefficient, the fourth sub-coefficient, and the fifth sub-coefficient in the evaluation period are marked as Z1, Z2, Z3, Z4, and Z5, respectively, and their corresponding weight values ​​are marked as Q1, Q2, Q3, Q4, and Q5, respectively, to obtain the delay coefficient in the evaluation period, which is recorded as R;

[0070]

[0071] The same method is adopted to obtain the delay coefficients in different evaluation periods, and the obtained delay coefficients are bound to the environmental parameters and equipment operation status parameters corresponding to the evaluation periods.

[0072] It should be further explained that, in a specific implementation process, the process of obtaining the actual delay sub-coefficient, combining the weight value to obtain the actual delay coefficient, and inputting it into a preset production prediction model to obtain the predicted production efficiency includes:

[0073] In the actual production process, the actual delay sub-coefficients of each production sub-process are monitored in real time, that is, the processing time of the unfinished production products from entering the production sub-process to leaving it, and the actual delay sub-coefficients include the actual first sub-coefficient, the actual second sub-coefficient, the actual third sub-coefficient, the actual fourth sub-coefficient, and the actual fifth sub-coefficient;

[0074] According to the current environmental parameters and equipment operation status parameters, the current weight values ​​of each production sub-process are obtained, that is, the weight values ​​obtained in the same evaluation cycle mentioned above, and the current actual delay coefficient is obtained according to the actual delay sub-coefficient and its corresponding weight value;

[0075] The preset process of the production prediction model is as follows: generating a production prediction set according to different delay coefficients and their corresponding production efficiencies, and dividing the obtained production prediction set into a training set and a test set;

[0076] Construct a convolutional neural network, use the delay coefficient in the training set as input data of the convolutional neural network, use the corresponding production efficiency in the training set as output data of the convolutional neural network, and train the convolutional neural network to obtain an initial convolutional neural network;

[0077] The initial convolutional neural network is verified using the test set, and the initial convolutional neural network with a preset test error threshold is output as the corresponding production prediction model. The actual delay coefficient is input into the production prediction model, and the corresponding predicted production efficiency is output through the production prediction model.

[0078] It should be further explained that, in the specific implementation process, the process of adjusting the speed of each production sub-process according to the predicted production efficiency includes:

[0079] Set expected production efficiency, which refers to the production efficiency that the staff expects the production equipment to achieve, use the production prediction model to obtain the predicted production efficiency of the production equipment in real time, and compare the predicted production efficiency with the expected production efficiency;

[0080] If the predicted production efficiency is greater than or equal to the expected production efficiency, no operation will be performed on it. If the predicted production efficiency is less than the expected production efficiency, the speed of each production sub-process will be adjusted to obtain the current actual delay sub-coefficient of each production sub-process. The speed adjustment refers to adjusting the processing speed of each production sub-process until its corresponding actual delay sub-coefficient returns to zero.

[0081] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A safety production management system based on big data analysis, characterized in that: Includes the following modules: The data acquisition module is used to collect environmental parameters, equipment operating status parameters, and actual production parameters, and build corresponding digital twin models; The safety monitoring module is used to set the safety production standards and compare the environmental parameters and equipment operation status parameters with the safety production standards to determine whether there are any safety production problems; A process division module is used to divide the production process to obtain several production sub-processes, and obtain the delay sub-coefficient of each production sub-process under different environmental parameters and equipment operation status parameters; The efficiency evaluation module is used to set the evaluation cycle, obtain the production efficiency under different environmental parameters and equipment operation status parameters, and construct the production efficiency curve. According to the production efficiency curve, the weight value of each production sub-process is obtained, and the corresponding delay coefficient is obtained in combination with the delay sub-coefficient; The production prediction module is used to obtain the actual delay sub-coefficient, combine the weight value to obtain the actual delay coefficient, and input it into the preset production prediction model to obtain the predicted production efficiency, and adjust the speed of each production sub-process according to the predicted production efficiency; The process of obtaining the weight value of each production sub-process and obtaining the delay coefficient includes: The production efficiency curve is regarded as a scatter plot, and its corresponding regression line is taken as the production efficiency line. The delay sub-coefficients under the environmental parameters and equipment operation status parameters corresponding to different evaluation cycles are added to the production efficiency line. The shortest distance between the coordinate point of the delay sub-coefficient in the same evaluation period and the production efficiency straight line is used as the weight value of the delay sub-coefficient in the evaluation period, including a first weight value, a second weight value, a third weight value, a fourth weight value, and a fifth weight value; According to the delay sub-coefficients in different evaluation periods and their corresponding weight values, the delay coefficient in each evaluation period is obtained, and the obtained delay coefficient is bound to the environmental parameters and equipment operation status parameters corresponding to its evaluation period.

2. The safety production management system based on big data analysis according to claim 1 is characterized in that: The environmental parameters include the workshop temperature, workshop humidity, and light intensity of the production workshop; the equipment operation status parameters include the equipment temperature, vibration amplitude, and equipment energy consumption of the production equipment; and the actual production parameters include the process parameters, production process, and quality standards of the production products; The construction process of the digital twin model includes: using CAD software to construct a geometric model of the production workshop and production equipment, constructing a physical model of the production equipment based on the geometric model, and integrating the geometric model and the physical model to obtain the corresponding digital twin model.

3. A safety production management system based on big data analysis according to claim 2, characterized in that: The process of setting production safety standards and determining whether there are production safety issues includes: The safety production standards include workshop temperature standards, workshop humidity standards, light intensity standards, equipment temperature standards, vibration amplitude standards, and equipment energy consumption standards; The relevant parameters in the environmental parameters and equipment operating status parameters are compared with their corresponding production safety standards. If the relevant parameters are not within the range of the production safety standards, it is judged that there is a production safety problem, and corresponding abnormal signals are generated according to the relevant parameters for feedback. When various abnormal signals appear, the production equipment is controlled to sound an alarm.

4. The safety production management system based on big data analysis according to claim 3 is characterized in that: The process of obtaining the production sub-process and its delay sub-coefficient includes: The production process refers to the entire process of producing products from raw material processing to finished products. According to the production situation of the products in the production process, the production process is divided into several production sub-processes, including the first sub-process, the second sub-process, the third sub-process, the fourth sub-process, and the fifth sub-process; Obtain the theoretical processing time of each production sub-process. In the digital twin model, adjust the relevant parameters in the environmental parameters and equipment operation status parameters respectively to obtain the simulated processing time of each production sub-process under different environmental parameters and equipment operation status parameters. According to the theoretical processing time and simulated processing time of each production sub-process, the delay sub-coefficients of each production sub-process under different environmental parameters and equipment operation status parameters are obtained, including the first sub-coefficient, the second sub-coefficient, the third sub-coefficient, the fourth sub-coefficient and the fifth sub-coefficient.

5. A production safety management system based on big data analysis according to claim 4, characterized in that: The process of setting up an evaluation cycle, obtaining production efficiency, and building a production efficiency curve includes: The production efficiency refers to the number of products produced by the production equipment in a single evaluation cycle. In the digital twin model, a set of environmental parameters and equipment operating status parameters are kept unchanged in a single evaluation cycle to obtain the production efficiency and its delay sub-coefficient in the evaluation cycle; The environmental parameters and equipment operation status parameters are adjusted to obtain the production efficiency and delay sub-coefficients in different evaluation cycles, the obtained evaluation cycles are numbered, and a production efficiency curve is constructed with the horizontal axis being the evaluation cycle and the vertical axis being the corresponding production efficiency.

6. A production safety management system based on big data analysis according to claim 5, characterized in that: The process of obtaining the actual delay sub-coefficient and the actual delay coefficient and inputting them into a preset production prediction model to obtain the predicted production efficiency includes: In the actual production process, the actual delay sub-coefficient of each production sub-process is monitored in real time, the current weight value of each production sub-process is obtained according to the current environmental parameters and equipment operation status parameters, and the current actual delay coefficient is obtained according to the actual delay sub-coefficient and its corresponding weight value; The preset process of the production prediction model is as follows: generating a production prediction set according to different delay coefficients and their corresponding production efficiencies, and dividing the production prediction set into a training set and a test set; Construct a convolutional neural network, use the delay coefficient in the training set as input data of the convolutional neural network, use the corresponding production efficiency in the training set as output data of the convolutional neural network, and train the convolutional neural network to obtain an initial convolutional neural network; The test set is used to verify the model of the initial convolutional neural network, and the output of the initial convolutional neural network that is less than or equal to the preset test error threshold is used as the corresponding production prediction model.

7. A production safety management system based on big data analysis according to claim 6, characterized in that: The process of speed regulation of each production sub-process includes: Set the expected production efficiency, use the production prediction model to obtain the predicted production efficiency of the production equipment in real time, compare the predicted production efficiency with the expected production efficiency, and if the predicted production efficiency is lower than the expected production efficiency, adjust the speed of each production sub-process. The speed adjustment refers to adjusting the processing speed of each production sub-process until the corresponding actual delay sub-coefficient returns to zero.

Images