Intelligent hardware for production safety decision

Abstract

The invention provides intelligent hardware for production safety decision, and relates to the technical field of data processing, and the intelligent hardware comprises a data collection module which is used for collecting physical quantities in a production environment and production equipment in real time; the data processing module is used for carrying out preprocessing and production bottleneck prediction on the acquired physical quantity data; the intelligent analysis and decision module is used for carrying out fault risk analysis and carrying out scheduling processing according to production bottleneck data and a fault risk analysis result, the fault risk analysis is divided into subjective risk factor analysis and objective risk factor analysis, and the subjective risk factor analysis adopts an intuitive fuzzy number to distribute a specific risk value; according to the method, uncertainty and fuzziness in the evaluation process can be processed, the evaluation result is closer to the actual situation, and objective risk factor analysis standardizes fault states at different time points to the same scale for comparison by calculating the relative value of the fault strength, so that the change trend of the equipment fault strength is reflected more accurately, and the evaluation accuracy is improved. And the risk assessment precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to intelligent hardware for production safety decision-making. Background Art

[0002] Intelligent manufacturing is the deep and comprehensive integration of traditional manufacturing industry with information and intelligent technology, so as to improve the scientificity and accuracy of various decisions in the industrial production process, and improve the level and efficiency of automatic control in the industrial manufacturing process. From the hardware level, intelligent manufacturing is manifested in the integration of various types of sensors and imaging equipment into each link of the production line to achieve comprehensive coverage and high real-time information perception; it also includes the use of the industrial Internet of wired and wireless media to achieve uplink and downlink communication transmission of information, data, and instructions to form a sustainable information flow. From the software level, intelligent manufacturing needs to establish a multi-source big data center and an intelligent decision-making center, so as to realize the construction, training and verification of various decision-making models based on big data, realize continuous optimization of intelligent decision-making, and then generate automatic control instructions issued to each link of the production line based on intelligent decision-making.

[0003] The production safety risk in each link of the production line is one of the key points of intelligent manufacturing. The production safety risk here covers all aspects of safety risks. At present, intelligent manufacturing in terms of production safety risks is mainly based on sensors and industrial Internet to monitor and alarm safety-related parameters, including the environmental parameters, state parameters, electrical variable parameters, equipment status values, etc. of each link, facility, and space of the production line. The perception, collection and uploading, then, make assessment decisions on production safety risks based on over-limit judgment, log analysis and other means, and take necessary monitoring, alarm, shutdown and other measures for the purpose of maintaining production safety.

[0004] At present, the main shortcomings of intelligent manufacturing technology in terms of production safety risks are the multi-type and multi-factor comprehensive models for all aspects of the production line, and the lack of an effective and reliable production safety risk decision-making system. Especially in certain production models, the above multi-type comprehensive factors also have the characteristics of rapid and complex changes, resulting in a high misjudgment rate and large time delay in production safety risk decisions, and it is impossible to take truly effective measures.

[0005] Therefore, it is necessary to provide a new intelligent hardware for production safety decision-making to solve the above technical problems. Summary of the invention

[0006] In order to solve the current multi-factor comprehensive model for various aspects of the production line, there is a lack of effective and reliable production safety risk decision-making system. In particular, in certain production modes, the above multi-type comprehensive factors also have the characteristics of rapid and complex changes, resulting in high misjudgment rate and large time delay in production safety risk decision-making, and the technical problem that truly effective measures cannot be taken, the present invention provides an intelligent hardware for production safety decision-making.

[0007] The intelligent hardware for production safety decision-making provided by the present invention includes a data acquisition module for real-time acquisition of physical quantities in the production environment and production equipment;

[0008] Data processing module, used to pre-process the collected physical quantity data and predict production bottlenecks;

[0009] Intelligent analysis and decision-making module, used to analyze the failure risk of production equipment according to the collected physical quantities and production bottleneck data, and to perform scheduling according to the production bottleneck data and failure risk analysis results;

[0010] Among them, the fault risk analysis is divided into subjective risk factor analysis and objective risk factor analysis. The subjective risk factor analysis is based on the maintenance manual content of the production equipment, assigns specific intuitive fuzzy numbers to each risk factor, and establishes an intuitive evaluation set of the corresponding subjective risk factors. The objective risk factor analysis subtracts the minimum fault intensity in the entire time interval from the fault intensity of the abnormal physical quantity at time t in the collected time interval to obtain a difference, determine the fault intensity range, and normalize the difference according to the fault intensity range in the entire time interval to obtain a relative value between 0 and 1. The dynamic changes of the production equipment in the time domain are obtained according to the subjective risk factor and objective risk factor analysis.

[0011] Furthermore, the production bottleneck prediction includes obtaining an exponential sequence of production data within a period of time, smoothing the exponential sequence of the production data by quoting an average weakening buffer operator, constructing a grey prediction model, and outputting a prediction result.

[0012] Furthermore, the fault intensity range is the maximum value of the abnormal physical quantity minus the minimum value of the abnormal physical quantity.

[0013] Furthermore, the physical quantity includes temperature, pressure value, and gas concentration.

[0014] Furthermore, the data acquisition module includes a temperature sensor, a pressure sensor, and a gas sensor, and each sensor converts the collected physical quantity into an electrical signal and transmits it to the data processing module.

[0015] Furthermore, preprocessing the collected physical quantity data includes filtering and denoising the collected physical quantity.

[0016] Furthermore, the scheduling process includes the following steps:

[0017] S1, select the production operation with the largest delay rate;

[0018] S2, randomly select an unfinished workpiece;

[0019] S3, select the workpiece that takes the shortest time on the earliest available machine in the processing process;

[0020] S4. Give priority to the production order with the shortest remaining processing time;

[0021] S5. Update the number of completed processes of the selected job;

[0022] S6. Repeat steps S1 to S5 until all operations are completed.

[0023] Furthermore, the delay rate is calculated as follows:

[0024]

[0025] Among them, n i is the total number of operations for job i, op i (t) is the number of processes currently completed by job i, is the average processing time of all available production equipment, D i is the expected completion time of job i, T c is the current time.

[0026] Furthermore, the scheduling process further includes the following steps:

[0027] S1. Determine the optimal maintenance time interval for a single production equipment under batch production;

[0028] S2. Establish a penalty function for a single production equipment;

[0029] S3. Determine the short-term maintenance window;

[0030] S4. Develop a combined maintenance plan;

[0031] S5. Dynamically update the combined maintenance plan according to changes in maintenance information.

[0032] Compared with the related art, the intelligent hardware for production safety decision-making provided by the present invention has the following advantages:

[0033] Beneficial effects:

[0034] 1. The subjective risk factor analysis in the present invention can take into account the role of human experience and knowledge in risk assessment by referring to the maintenance manual content, and capture those risk factors that are difficult to directly quantify. This helps to identify the impact of subjective aspects such as human operation and management decision-making on equipment failures, while the objective risk factor analysis is based on actual data, and reflects the impact of the physical state of the equipment itself and the external environment on equipment performance by quantifying the changes in the intensity of the failure. Quantitative analysis can provide more specific and objective risk information, and can more comprehensively understand the operating status of production equipment, which helps to timely discover and eliminate potential safety hazards and failure factors, improve the reliability and stability of equipment, and reduce the possibility of human intervention and erroneous operation.

[0035] 2. The present invention performs scheduling processing by understanding the dynamic changes of production equipment in the time domain. During the period when equipment failures are most likely to occur, maintenance and replacement plans can be arranged in advance to avoid production interruptions. During the period when equipment performance is stable, production load can be increased to improve production efficiency.

[0036] 3. The subjective risk factor analysis of the present invention adopts intuitive fuzzy numbers to assign specific risk values, which can handle the uncertainty and ambiguity in the evaluation process and make the evaluation results closer to the actual situation. The objective risk factor analysis calculates the relative value of the fault intensity and standardizes the fault status at different time points to the same scale for comparison, thereby more accurately reflecting the changing trend of equipment fault intensity and improving the accuracy of risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A system block diagram of the intelligent hardware for production safety decision-making provided by the present invention;

[0038] Figure 2 The flow chart of the scheduling process provided by the present invention Figure 1 ;

[0039] Figure 3 The flow chart of the scheduling process provided by the present invention Figure 2 ;

[0040] Figure 4 A flowchart of the production bottleneck prediction provided by the present invention;

[0041] Figure 5 A flowchart of building a grey prediction model provided by the present invention;

[0042] Figure 6 A flowchart of the intuitive fuzzy number allocation provided by the present invention. DETAILED DESCRIPTION

[0043] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0044] Please refer to Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 as well as Figure 6 ,in, Figure 1 A system block diagram of the intelligent hardware for production safety decision-making provided by the present invention; Figure 2 The flow chart of the scheduling process provided by the present invention Figure 1 ; Figure 3 The flow chart of the scheduling process provided by the present invention Figure 2 ; Figure 4 A flowchart of the production bottleneck prediction provided by the present invention; Figure 5 A flowchart of building a grey prediction model provided by the present invention; Figure 6 A flowchart of the intuitive fuzzy number allocation provided by the present invention.

[0045] In the specific implementation process, Figure 1-Figure 6 As shown, the intelligent hardware for production safety decision-making includes a data acquisition module, which is used to collect physical quantities in the production environment and production equipment in real time, where the physical quantities include temperature, pressure value, and gas concentration. The data acquisition module includes a temperature sensor, a pressure sensor, and a gas sensor. Each sensor converts the collected physical quantity into an electrical signal and transmits it to the data processing module;

[0046] Data processing module, used to pre-process the collected physical quantity data and predict production bottlenecks;

[0047] Intelligent analysis and decision-making module, used to analyze the failure risk of production equipment according to the collected physical quantities and production bottleneck data, and to perform scheduling according to the production bottleneck data and failure risk analysis results;

[0048] Among them, the failure risk analysis is divided into subjective risk factor analysis and objective risk factor analysis. The subjective risk factor analysis is based on the maintenance manual content of the production equipment. A specific intuitive fuzzy number is assigned to each risk factor x∈U, and an intuitive evaluation set of the corresponding subjective risk factors is established, which is expressed as:

[0049]

[0050] in, are the upper and lower limits of the evaluation set membership, that is, the minimum and maximum possibilities of element x belonging to a certain evaluation level, are the upper and lower limits of the non-membership degree of the evaluation set, that is, the minimum and maximum possibilities that element x does not belong to a certain evaluation level, are the upper and lower limits of the hesitation of the evaluation set, i.e., the minimum and maximum range of uncertainty of the evaluator when judging that element x belongs to a certain evaluation level;

[0051] refer to Figure 6 As shown, the intuitionistic fuzzy number allocation process is:

[0052] 1. Select the risk factor and set the risk factor x to the degree of wear of machine parts;

[0053] 2. Determine the evaluation level: There are three evaluation levels: low, medium and high;

[0054] 3. Assign intuitive fuzzy numbers: For the "low" evaluation level, the wear degree of machine parts is very likely to be low, but there is a certain uncertainty. The membership interval can be set to [0.7, 0.9] (indicating that there is at least a 70% to 90% probability of being low), the non-membership interval is [0.05, 0.2] (indicating that there is at most a 5% to 20% probability of not being low), and the hesitation interval is [0.1-(0.05+0.2), 0.3-(0.7+0.2)] = [0.05, 0.1] (it should be noted that the normalization condition ux+vx+wx=1 is used here to calculate the hesitation interval). The "medium" evaluation level and the "high" evaluation level are similar to the above;

[0055] 4. Construct a complete evaluation set:

[0056] S = {"Degree of wear of machine parts", ([0.7, 0.9], [0.05, 0.2], [0.05, 0.1]) Low, ... (similar intuitive fuzzy numbers are assigned to medium and high evaluation levels)};

[0057] The objective risk factor analysis obtains a difference by subtracting the minimum fault intensity in the entire time interval from the fault intensity of the abnormal physical quantity at time t in the collected time interval, determines the fault intensity range, and normalizes the difference according to the fault intensity range in the entire time interval, thereby obtaining a relative value between 0 and 1. The subjective risk factor analysis of the present invention uses intuitive fuzzy numbers to assign specific risk values, which can handle the uncertainty and ambiguity in the evaluation process and make the evaluation results closer to the actual situation. The objective risk factor analysis calculates the relative value of the fault intensity and standardizes the fault states at different time points to the same scale for comparison, thereby more accurately reflecting the changing trend of the equipment fault intensity and improving the accuracy of risk assessment.

[0058] It should be noted that the fault intensity range is the maximum value of the abnormal physical quantity minus the minimum value of the abnormal physical quantity:

[0059] Assume that the time interval for collecting physical quantities [t b ,t e The maximum and minimum values ​​of the fault intensity in the max (t b ,t e ) and wmin (t b ,t e ), then the abnormal physical quantity FM j At time t, t∈[t b ,t e ] is:

[0060]

[0061] It should be noted that t b and t e Respectively represent the start and end time of the time interval;

[0062] w(t|FM j ,EP) indicates that at time t, given the abnormal physical quantity FM j and failure intensity under certain environmental or operating conditions EP;

[0063] w max (t b ,t e ) and w min (t b ,t e ) respectively represent the time interval [t b ,t e ], the maximum and minimum values ​​of the fault intensity of all abnormal physical quantities;

[0064] Obtain the dynamic changes of production equipment in the time domain based on subjective and objective risk factor analysis. By comprehensively analyzing subjective and objective risk factors, risk factor analysis is an ongoing process that requires continuous collection and analysis of new data and information. This can provide a more comprehensive understanding of the operating status of production equipment, which helps to timely discover and eliminate potential safety hazards and failure factors, improve equipment reliability and stability, and reduce the possibility of human intervention and erroneous operation.

[0065] Further, refer to Figure 4 As shown in the figure, production bottleneck prediction includes obtaining an exponential sequence of production data over a period of time θ = (θ1, θ2, …, θ g ,…,θ n ), the average weakening buffer operator is used to smooth the exponential sequence of production data, a grey prediction model is constructed, and the prediction results are output:

[0066] The exponential series of production data is smoothed by applying the average weakening buffer operator:

[0067] X=θD=(θ1d,θ2d,…,θ g d,…,θ n d)

[0068]

[0069] g=3,4…,n-1

[0070] For the first two elements of the sequence (i.e. g = 1, 2), this smoothing is usually not applied because they do not have enough subsequent elements to calculate the average.

[0071] refer to Figure 5 As shown, the grey prediction model includes the following:

[0072] 1. Accumulation generation: Accumulate the smoothed data sequence X to obtain a new data sequence X1;

[0073] 2. Establish differential equations: Based on the cumulative generation sequence X1, establish a first-order linear differential equation

[0074]

[0075] 3. Parameter estimation: Estimate parameters a and b using methods such as least squares;

[0076] 4. Model solution: obtain the prediction model by solving the differential equation;

[0077] 5. Input: Enter the time point or time interval to be predicted;

[0078] 6. Prediction value: Calculate the corresponding prediction value according to the prediction model;

[0079] 7. Output: Output the prediction results and conduct necessary analysis and explanation.

[0080] Furthermore, preprocessing the collected physical quantity data includes filtering and denoising the collected physical quantity;

[0081] In one embodiment, reference Figure 2 As shown, the scheduling process includes the following steps:

[0082] S1, select the production operation with the largest delay rate;

[0083] S2, randomly select an unfinished workpiece;

[0084] S3, select the workpiece that takes the shortest time on the earliest available machine in the processing process;

[0085] S4. Give priority to the production order with the shortest remaining processing time;

[0086] S5. Update the number of completed processes of the selected job;

[0087] S6. Repeat steps S1 to S5 until all operations are completed.

[0088] Furthermore, the delay rate is calculated as follows:

[0089]

[0090] Among them, n i is the total number of operations for job i, op i (t) is the number of processes currently completed by job i, is the average processing time of all available production equipment, D i is the expected completion time of job i, T c is the current time;

[0091] Specific calculation steps:

[0092] 1. Determine the current time: First, determine the current time T c ;

[0093] 2. Determine the current status of job i: Find out the current status of job i at the current time T c The number of completed operations op i (t);

[0094] 3. Calculate the average processing time of the remaining processes: For each remaining process (from op i (t)+1 to n i ), calculate its average processing time Add these average processing times to get the total processing time for the remaining steps

[0095] 4. Calculate the delay: Subtract the expected completion time D of job i from the total processing time of the remaining processes i (If D i If the result is less than or equal to the total processing time of the remaining processes, the result is positive, indicating a delay; if it is negative, it may mean that the expected time is set too long or the calculation is wrong). It should be noted that the formula here does not actually directly subtract D i , but the sum of the average processing time of the remaining processes is calculated. Since the delay rate is calculated by comparing the actual completion time with the expected time, in practical applications, this sum needs to be further processed to obtain the delay rate (for example, by comparing it with D i or a benchmark time for comparison).

[0096] refer to Figure 3 As shown, the scheduling process also includes the following steps:

[0097] S1. Determine the optimal maintenance time interval for a single production equipment under batch production;

[0098] S2. Establish a penalty function for a single production equipment;

[0099] S3. Determine the short-term maintenance window to ensure that each component is maintained at least once and allow the component to perform multiple maintenance activities;

[0100] S4. Develop a combined maintenance plan, aiming at the combination with the lowest cost;

[0101] S5. Dynamically update the combined maintenance plan according to changes in maintenance information.

[0102] Experiment 1

[0103] In order to verify the effect of the present invention on scheduling processing, 6 production equipment are randomly selected, which are defined as A1, A2, A3, A4, A5, and A6. The fault locations, maintenance effects, and damage after maintenance of the 6 production equipment are tested respectively. The test results are as follows:

[0104]

[0105] It can be seen from the above table that the present invention greatly improves the maintenance effect by formulating a combined maintenance plan, determining a short-term maintenance window, ensuring that each component is maintained at least once, and allowing components to perform multiple maintenance activities.

[0106] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0107] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention, and any figure mark in the claims should not be regarded as limiting the claims involved.

[0108] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. An intelligent hardware for production safety decision-making, characterized in that: It includes a data acquisition module for real-time acquisition of physical quantities in the production environment and production equipment; Data processing module, used to pre-process the collected physical quantity data and predict production bottlenecks; Intelligent analysis and decision-making module, used to analyze the failure risk of production equipment according to the collected physical quantities and production bottleneck data, and to perform scheduling according to the production bottleneck data and failure risk analysis results; Among them, the fault risk analysis is divided into subjective risk factor analysis and objective risk factor analysis. The subjective risk factor analysis is based on the maintenance manual content of the production equipment, assigns specific intuitive fuzzy numbers to each risk factor, and establishes an intuitive evaluation set of the corresponding subjective risk factors. The objective risk factor analysis subtracts the minimum fault intensity in the entire time interval from the fault intensity of the abnormal physical quantity at time t in the collected time interval to obtain a difference, determine the fault intensity range, and normalize the difference according to the fault intensity range in the entire time interval to obtain a relative value between 0 and 1. The dynamic changes of the production equipment in the time domain are obtained according to the subjective risk factor and objective risk factor analysis.

2. The intelligent hardware for production safety decision-making according to claim 1, characterized in that: The production bottleneck prediction includes obtaining an exponential sequence of production data within a period of time, smoothing the exponential sequence of the production data by quoting an average weakening buffer operator, building a grey prediction model, and outputting a prediction result.

3. The intelligent hardware for production safety decision-making according to claim 1, characterized in that: The fault intensity range is the maximum value of the abnormal physical quantity minus the minimum value of the abnormal physical quantity.

4. The intelligent hardware for production safety decision-making according to claim 1, characterized in that: The physical quantities include temperature, pressure value, and gas concentration.

5. The intelligent hardware for production safety decision-making according to claim 1, characterized in that: The data acquisition module includes a temperature sensor, a pressure sensor, and a gas sensor. Each sensor converts the collected physical quantity into an electrical signal and transmits it to the data processing module.

6. The intelligent hardware for production safety decision-making according to claim 1, characterized in that: Preprocessing the collected physical quantity data includes filtering and denoising the collected physical quantity.

7. The intelligent hardware for production safety decision-making according to claim 1, characterized in that: The scheduling process comprises the following steps: S1, select the production operation with the largest delay rate; S2, randomly select an unfinished workpiece; S3, select the workpiece that takes the shortest time on the earliest available machine in the processing process; S4. Give priority to the production order with the shortest remaining processing time; S5. Update the number of completed processes of the selected job; S6. Repeat steps S1 to S5 until all operations are completed.

8. The intelligent hardware for production safety decision-making according to claim 7, characterized in that: The delay rate is calculated as follows: Among them, n i is the total number of operations for job i, op i (t) is the number of processes currently completed by job i, is the average processing time of all available production equipment, D i is the expected completion time of job i, T c is the current time.

9. The intelligent hardware for production safety decision-making according to claim 8, characterized in that: The scheduling process also includes the following steps: S1. Determine the optimal maintenance time interval for a single production equipment under batch production; S2. Establish a penalty function for a single production equipment; S3. Determine the short-term maintenance window; S4. Develop a combined maintenance plan; S5. Dynamically update the combined maintenance plan according to changes in maintenance information.

Images