Air separation production line health degree evaluation method, system and equipment

Abstract

The invention relates to the technical field of equipment health evaluation, in particular to an air separation production line health degree evaluation method, system and equipment, and the method comprises the following steps: S1, dividing an air separation production line into a primary subsystem layer, an evaluation dimension layer and an evaluation index layer from top to bottom; s2, collecting index real-time data, and calculating a real-time health degree score of each index according to a relationship between the index real-time data and a preset state threshold value; s3, dynamically calculating the real-time weight of each index based on the degree of deviation of the index real-time data from the threshold value; s4, calculating a dimension score of each evaluation dimension according to the score and the weight of each index; s5, calculating a health degree score of each primary subsystem according to the score of each dimension and a preset dimension weight; and S6, calculating and outputting an overall health degree evaluation result of the space division production line according to the score of each subsystem and a preset subsystem weight. According to the method, comprehensive, dynamic and quantitative evaluation of the health state of the air separation production line is realized, and layer-by-layer accurate positioning of faults is supported.

Description

Technical Field

[0001] This invention relates to the field of equipment health assessment technology, and in particular to a method, system and equipment for evaluating the health of an air separation production line. Background Technology

[0002] As a key industrial equipment, the long-term stable operation of air separation production lines is crucial for ensuring continuous production. Traditional equipment condition monitoring and health management methods have the following limitations: Traditional methods typically rely on single sensors (such as vibration or temperature) to monitor specific components and set fixed alarm thresholds based on experience. This approach fails to reflect the overall operating status of complex production lines, and fixed thresholds are ill-suited to adapt to dynamic changes in equipment under different operating conditions and life stages, easily leading to false alarms or missed alarms. Existing methods largely focus on fault diagnosis or abnormal alarms, lacking a quantitative evaluation of the overall health of the equipment. Even using statistical models (such as reliability models and survival analysis) for assessment heavily relies on a large amount of historical fault data, but complete fault data from industrial sites is often difficult to obtain, making model building challenging and hindering real-time, intuitive health scoring.

[0003] When comprehensively evaluating multiple parameters, existing methods often employ fixed weights. However, in actual operation, the severity represented by the same parameter varies across different numerical ranges, and its contribution (i.e., weight) to overall health should be dynamically changing.

[0004] Therefore, there is an urgent need for a quantitative evaluation method for the health of air separation production lines that can overcome the above-mentioned defects, achieve multi-level and multi-parameter fusion, and dynamically adaptive weights, so as to reflect the overall health status of the production line in real time and intuitively, accurately locate potential risk points, and provide a scientific basis for predictive maintenance. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by providing a method for evaluating the health of an air separation production line, comprising the following steps: S1: Divide the air separation production line to be evaluated into several first-level subsystem layers, several evaluation dimension layers under each first-level subsystem, and several evaluation index layers under each evaluation dimension, according to the functional level from top to bottom. S2: Collect monitoring data of all evaluation indicators in real time, and calculate the real-time health score of each evaluation indicator based on the relationship between the real-time data of each evaluation indicator and several preset status thresholds. S3: Based on the deviation between the real-time data of each evaluation indicator and the preset number of state thresholds, dynamically calculate the real-time weight of each evaluation indicator. S4: Calculate the dimensional score of each evaluation dimension based on the real-time health score of each evaluation indicator and its corresponding real-time weight. S5: Calculate the health score of each first-level subsystem layer based on the dimensional scores and preset dimensional weights; S6: Calculate and output the overall health evaluation result of the air separation production line based on the health scores of each first-level subsystem layer and the preset subsystem weights.

[0006] Preferably, in step S1, dividing the air separation production line to be evaluated into functional levels from top to bottom includes: The air separation production line to be evaluated is divided into several primary subsystem layers according to the air separation process flow, including an air compressor system, a precooling system, a purification system, a booster compressor system, and a fractionation tower system. The evaluation dimension layer is divided according to the key equipment or functional modules within the first-level subsystem layer; The evaluation index layer is divided into evaluation parameters based on the physical parameters under the evaluation dimension layer, including vibration, temperature, pressure, displacement, power, and flow rate.

[0007] Preferably, in step S2, the real-time health score of each evaluation indicator is calculated based on the relationship between the real-time data of each evaluation indicator and several preset state thresholds, including: The aforementioned state thresholds divide the numerical range of the indicator into several continuous state intervals, including the normal interval, the warning interval, and the alarm interval. The real-time data is compared with the state threshold to determine the state interval to which it belongs; Based on the pre-defined baseline score calculation rules for the determined state interval, the real-time health score of this evaluation indicator is calculated.

[0008] Preferably, the benchmark score calculation rule is a piecewise function, including: Based on the real-time detection value x of the evaluation index, the preset eight state thresholds are: < < < < < < < Calculate the real-time health score y, as shown below: ,in, , .

[0009] Preferably, in step S3, the real-time weights of each evaluation index are dynamically calculated, including: Based on the real-time detection value x of the evaluation index, the real-time weight w is calculated as follows: in, It is the core normal range, x < It is a shutdown / invalid interval. This is the preset upper limit of the weight.

[0010] Preferably, in step S4, the score for each evaluation dimension is calculated based on the score of each evaluation indicator and its corresponding real-time weight, including: Where "score" represents the score for the evaluation dimension. Let be the real-time weight of the i-th evaluation metric in this dimension layer. is the real-time health score of this evaluation indicator, and n is the total number of evaluation indicators under this evaluation dimension.

[0011] Preferably, in step S5, the health score of each first-level subsystem layer is calculated based on the scores of each evaluation dimension and the preset dimension weights, including: The weighted summation method is used to calculate the health score (SubsysScore) of the first-level subsystem layer, as shown in the following formula: in, Let be the preset dimension weight of the i-th evaluation dimension under the first-level subsystem layer, and satisfy . , Let be the score of the i-th evaluation dimension layer, and m be the total number of evaluation dimension layers under the first-level subsystem layer.

[0012] Preferably, in step S6, the overall health evaluation result of the air separation production line is calculated and output, including: The weighted summation method was used to calculate the overall health evaluation results of the air separation production line. The formula is as follows: in, Let be the preset subsystem weights of the j-th first-level subsystem layer, and satisfy . , Let p be the health score of the j-th first-level subsystem layer, and p be the total number of first-level subsystem layers.

[0013] Based on the same concept, the present invention also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor causes the processor to perform the steps of an air separation production line health evaluation method as described in the embodiments.

[0014] Based on the same concept, the present invention also provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of an air separation production line health evaluation method as described in any one of the embodiments.

[0015] Compared with the prior art, the beneficial effects of the present invention are: (1) This invention divides the air separation production line into a multi-level evaluation system from top to bottom, consisting of a first-level subsystem layer, an evaluation dimension layer, and an evaluation index layer. It also performs real-time data collection and health calculation on each layer's indicators, thus achieving a comprehensive evaluation of the health status from local parameters to the overall system. This overcomes the limitations of traditional methods that only monitor a single component or parameter, and can more accurately and comprehensively reflect the overall operating status of the production line.

[0016] (2) This invention dynamically calculates the real-time weight of each evaluation indicator based on the deviation between the real-time data of each evaluation indicator and the preset state threshold, and aggregates and calculates the scores of the upper dimension and the system accordingly, thereby realizing the adaptive adjustment of the evaluation weight: when the parameter deviates from the normal range, its weight automatically increases, thereby highlighting the influence of abnormal parameters in the overall evaluation, making the health assessment results more realistically reflect the distribution of actual operational risks, and improving the sensitivity and accuracy of the assessment.

[0017] (3) This invention integrates dynamic weight calculation, multi-level weighted aggregation, and preset weight normalization to finally output a quantitative overall health score for the air separation production line, achieving an intuitive and comprehensive quantitative evaluation of the health status of complex production lines. This method does not rely on a large amount of historical fault data, can adapt to different working conditions, and can locate potential risk sources through score change trends and hierarchical decomposition, thereby providing a real-time and reliable basis for predictive maintenance and operation decisions. It has the advantages of comprehensive evaluation, strong adaptability, and high practicality. Attached Figure Description

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention.

[0019] Figure 1 This is a flowchart of a method for evaluating the health of an air separation production line according to the present invention; Figure 2 This is another flowchart of a method for evaluating the health of an air separation production line according to the present invention; Figure 3 This is a diagram showing the division of an air separation production line according to the health evaluation method for an air separation production line of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. Obviously, the described embodiments are only some, not all, of the embodiments described in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without creative effort are within the scope of protection of this application.

[0021] Those skilled in the art will understand that, unless otherwise stated, the singular forms “a” and “an” used herein, and “the”, may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0022] First Embodiment Please see Figure 1 and Figure 2 As shown, this embodiment provides a method for evaluating the health of an air separation production line, including the following steps: S1: The air separation production line to be evaluated is divided into several first-level subsystem layers, several evaluation dimension layers under each first-level subsystem, and several evaluation index layers under each evaluation dimension from top to bottom according to the functional level. Specifically, in this embodiment, the booster system of a large air separation production line is taken as an example.

[0023] Please see Figure 3 As shown, in step S1, dividing the air separation production line to be evaluated into functional levels from top to bottom includes: The air separation production line to be evaluated is divided into several primary subsystems according to the air separation process flow, including an air compressor system, a precooling system, a purification system, a product compression system, a storage and transportation system, a booster compressor system, and a fractionation tower system. Specifically, in this embodiment, the air separation production line is divided into multiple subsystems according to the process flow. This embodiment focuses on the booster compressor system, which is responsible for providing compressed air; the precooling system performs preliminary cooling of the compressed air; the purification system removes impurities such as moisture and carbon dioxide from the air; the booster compressor system further pressurizes the air; the fractionation tower system separates nitrogen, oxygen, and other products through low-temperature distillation; the product compression system pressurizes the product gas; and the storage and transportation system stores and transports the product. The evaluation dimension layer is divided according to the key equipment or functional modules within the first-level subsystem layer. Specifically, in this embodiment, for equipment-intensive subsystems, the dimensions can be divided according to key equipment (e.g., compressor body, drive motor, cooling system, etc.), and for process-type subsystems, the dimensions can be divided according to key functions (e.g., heat exchange efficiency, separation efficiency, control stability, etc.; in this embodiment, the booster compressor body and booster compressor motor are selected as two dimensions). The evaluation dimension layer is divided into several evaluation index layers based on the physical parameters. These include vibration (vibration velocity, vibration displacement, vibration acceleration), temperature (bearing temperature, winding temperature, cooling medium temperature), pressure (intake pressure, exhaust pressure, pressure difference), displacement, power, and flow rate. Specifically, in this embodiment, the evaluation dimension is the turbocharger body, and the evaluation index for the turbocharger body is vibration (mm / s). The turbocharger is identified as Vib_B, and the index includes shaft displacement (Disp_B). The evaluation dimension is the turbocharger motor, and the evaluation index includes vibration (Vib_M), bearing temperature, cold air temperature, power, and other indicators.

[0024] S2: Collect monitoring data of all evaluation indicators in real time, and calculate the real-time health score of each evaluation indicator based on the relationship between the real-time data of each evaluation indicator and several preset status thresholds.

[0025] Preferably, in step S2, the real-time health score of each evaluation indicator is calculated based on the relationship between the real-time data of each evaluation indicator and several preset state thresholds, including: The aforementioned state thresholds divide the numerical range of the indicator into several continuous state intervals, including the normal interval, the warning interval, and the alarm interval. The real-time data is compared with the state threshold to determine the state interval to which it belongs; Based on the pre-defined baseline score calculation rules for the determined state interval, the real-time health score of this evaluation indicator is calculated.

[0026] Preferably, the benchmark score calculation rule is a piecewise function, including: Based on the real-time detection value x of the evaluation index, the preset eight state thresholds are: < < < < < < < The real-time health score y (out of 100) is calculated. The design principle is that a high score or full score is awarded when the value is within the optimal range, and the score decreases as the value deviates further from the optimal range, as shown below: ,in, , Specifically, in this embodiment, taking the vibration index of the booster compressor body (Vib_B) as an example, its threshold is set as follows: t1=0, t2=5, t3=8, t4=13.5, t5=24.5, t6=30, t7=99, t8=122 (unit: mm / s). The real-time value of the booster compressor body vibration is x = 30.1 mm / s. According to its threshold, x satisfies t6 (30)≤x < t7 (99), so it falls into the alarm range. y = 80 - 20 × (x -t6) / (t7 - t6) = 80 - 20 × (30.1 - 30) / (99 - 30)≈ 79.97.

[0027] S3: Based on the deviation between the real-time data of each evaluation indicator and the preset state thresholds, the real-time weight of each evaluation indicator is dynamically calculated. Specifically, in this embodiment, in traditional methods, the weight of each indicator is usually a fixed value, which cannot reflect the relative importance changes of different parameter states during equipment operation. For example, the vibration weight may not be high under normal circumstances, but when the vibration value spikes abnormally, it should immediately become the most concerned indicator. Through the dynamic weight mechanism, the system can automatically identify and "focus" on those indicators that are deteriorating or are already in a serious state, so that the final health score more realistically reflects the most pressing health risks. As an influencing factor, the weight quantifies the negative impact of the deterioration of a single indicator on the health level of the subsystem and even the entire production line.

[0028] Preferably, in step S3, the real-time weights of each evaluation index are dynamically calculated, including: Based on the real-time detection value x of the evaluation index, the real-time weight w is calculated as follows: in, It is the core normal range, x < It is a shutdown / invalid interval. The preset upper limit of the weight is used. Specifically, in this embodiment, taking the vibration of the booster compressor body (Vib_B) as an example, its real-time value x = 30.1 mm / s falls within the interval t6 ≤ x < t7, and the upper limit of the weight is set accordingly. Given 5, calculate its real-time weight w: w = exp( ( (x-t5) / t5 )^2 + ( (x-t6) / t6 )^2 )= exp( ( (30.1-24.5) / 24.5 )^2 + ( (30.1-30) / 30)^2 )≈ exp(0.0544 + 0.00001) ≈ 1.056. To demonstrate dynamism, compare the vibration of the booster motor (Vib_M). Its real-time value x=15.82, which is in the interval t6 (15) ≤ x < t7 (56). The calculated weight w ≈ 1.031. For indicators in the core normal interval (t4 ≤ x < t5), such as bearing temperature 1 (Temp_B1) (x=70.8, in t5 ≤ x < t6, the calculation is incorrect, it should be an example of the normal interval), its weight w = 1.

[0029] Among them, if a certain indicator corresponds to 6 thresholds, that is ( , , , , , The score and weight calculation function for example: Based on the real-time detection value x of the evaluation index, the real-time weight w is calculated as follows: In Formula 5 , S4: Calculate the dimensional score of each evaluation dimension based on the real-time health score of each evaluation indicator and its corresponding real-time weight.

[0030] Preferably, in step S4, the score for each evaluation dimension is calculated based on the score of each evaluation indicator and its corresponding real-time weight, including: Where "score" represents the score for the evaluation dimension. Let be the real-time weight of the i-th evaluation metric in this dimension layer. This represents the real-time health score of the evaluation indicator, where n is the total number of evaluation indicators under this evaluation dimension. Specifically, in this embodiment, taking the booster compressor body dimension as an example, it includes four indicators: Vib_B, Temp_B1, bearing temperature Temp_B2, and shaft displacement Disp_B. The scores of each indicator are known. and weight Calculate the score for this dimension. : (Ontology) = = (1.056×79.97+1×100+1×100+1×100) / (1.056+1+1+1)≈379.97 / 4.056 ≈ 93.70. Similarly, calculate the score for the booster motor dimension, weight... Here, the indicator that acts as an influencing factor has a higher weight because it indicates a worse state (lower score). Generally, the larger the value, the more amplified the downward pull of low-scoring indicators on the final average score in a weighted average, making the dimensional scores more sensitive to outliers. (Divided by the weights...) This is to eliminate the incomparability caused by different total weights between different dimensions, ensure that the score always falls within a reasonable range (such as 0-100 points), and reflect the weighted average level of each indicator's status.

[0031] S5: Calculate the health score of each first-level subsystem layer based on the dimensional scores and preset dimensional weights.

[0032] Preferably, in step S5, the health score of each first-level subsystem layer is calculated based on the scores of each evaluation dimension and the preset dimension weights, including: The weighted summation method is used to calculate the health score (SubsysScore) of the first-level subsystem layer, as shown in the following formula: in, Let be the preset dimension weight of the i-th evaluation dimension under the first-level subsystem layer, and satisfy . , Let m be the score of the i-th evaluation dimension layer, and m be the total number of evaluation dimension layers under the first-level subsystem layer. Specifically, in this embodiment, given the known scores of the booster compressor body dimension (Score_body = 93.70) and the booster compressor motor dimension (Score_motor = 94.89), preset normalization weights are assigned to the two dimensions, for example, W_body = 0.6 and W_motor = 0.4 (satisfying...). ), calculate the score of the booster subsystem. : = = 0.6×93.70 + 0.4×94.89 ≈ 94.18.

[0033] S6: Based on the health scores of each first-level subsystem and the preset subsystem weights, calculate and output the overall health evaluation result of the air separation production line. Specifically, in this embodiment, repeat the above steps S1-S5 to calculate the health scores of all 17 first-level subsystems of the air separation production line.

[0034] Preferably, in step S6, the overall health evaluation result of the air separation production line is calculated and output, including: The weighted summation method was used to calculate the overall health evaluation results of the air separation production line. The formula is as follows: in, Let be the preset subsystem weights of the j-th first-level subsystem layer, and satisfy . , Let be the health score of the j-th first-level subsystem layer, and p be the total number of first-level subsystem layers. Specifically, in this embodiment, assuming the weight of the booster subsystem ω_booster = 0.15, the overall health evaluation result H of the entire air separation production line is calculated. The weighted scores of the 17 subsystems are summed to obtain a final health score between 0 and 100. For example, the current health of the air separation production line is 92.5. This score intuitively reflects the overall operating status of the production line, and can be drilled down to view the scores and weights of each subsystem, dimension, and even specific indicator, achieving layer-by-layer positioning of health status. The health score of the air separation production line is shown in Table 1 below: Table 1: Health Score of Air Separation Production Line Second Embodiment Based on the same concept, this embodiment also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor performs the steps of an air separation production line health evaluation method as described in the embodiment.

[0035] Based on the same concept, the present invention also provides a storage medium storing computer-readable instructions, characterized in that, when the computer-readable instructions are executed by one or more processors, the one or more processors cause the one or more processors to perform the steps of an air separation production line health evaluation method as described in any one of the embodiments.

[0036] It is understood that, for the aforementioned method for evaluating the health of an air separation production line, if all of these methods are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer server or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this invention. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0037] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0038] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A method for evaluating the health of an air separation production line, characterized in that, Includes the following steps: S1: Divide the air separation production line to be evaluated into several first-level subsystem layers, several evaluation dimension layers under each first-level subsystem, and several evaluation index layers under each evaluation dimension, according to the functional level from top to bottom. S2: Collect monitoring data of all evaluation indicators in real time, and calculate the real-time health score of each evaluation indicator based on the relationship between the real-time data of each evaluation indicator and several preset status thresholds. S3: Based on the deviation between the real-time data of each evaluation indicator and the preset number of state thresholds, dynamically calculate the real-time weight of each evaluation indicator. S4: Calculate the dimensional score of each evaluation dimension based on the real-time health score of each evaluation indicator and its corresponding real-time weight. S5: Calculate the health score of each first-level subsystem layer based on the dimensional scores and preset dimensional weights; S6: Calculate and output the overall health evaluation result of the air separation production line based on the health scores of each first-level subsystem layer and the preset subsystem weights.

2. The method for evaluating the health of an air separation production line according to claim 1, characterized in that, In step S1, dividing the air separation production line to be evaluated into functional levels from top to bottom includes: The air separation production line to be evaluated is divided into several primary subsystem layers according to the air separation process flow, including an air compressor system, a precooling system, a purification system, a booster compressor system, and a fractionation tower system. The evaluation dimension layer is divided according to the key equipment or functional modules within the first-level subsystem layer; The evaluation index layer is divided into evaluation parameters based on the physical parameters under the evaluation dimension layer, including vibration, temperature, pressure, displacement, power, and flow rate.

3. The method for evaluating the health of an air separation production line according to claim 1, characterized in that, In step S2, based on the relationship between the real-time data of each evaluation indicator and several preset state thresholds, the real-time health score of each evaluation indicator is calculated, including: The aforementioned state thresholds divide the numerical range of the indicator into several continuous state intervals, including the normal interval, the warning interval, and the alarm interval. The real-time data is compared with the state threshold to determine the state interval to which it belongs; Based on the pre-defined baseline score calculation rules for the determined state interval, the real-time health score of this evaluation indicator is calculated.

4. The method for evaluating the health of an air separation production line according to claim 3, characterized in that, The benchmark score calculation rule is a piecewise function, including: Based on the real-time detection value x of the evaluation index, the preset eight state thresholds are: < < < < < < < Calculate the real-time health score y, as shown below: , in, , .

5. The method for evaluating the health of an air separation production line according to claim 4, characterized in that, In step S3, the real-time weights of each evaluation index are dynamically calculated, including: Based on the real-time detection value x of the evaluation index, the real-time weight w is calculated as follows: in, It is the core normal range, x < It is a shutdown / invalid interval. This is the preset upper limit of the weight.

6. The method for evaluating the health of an air separation production line according to claim 1, characterized in that, In step S4, the score for each evaluation dimension is calculated based on the score of each evaluation indicator and its corresponding real-time weight, including: Where "score" represents the score for the evaluation dimension. This represents the real-time weight of the i-th evaluation metric within this dimension. is the real-time health score of this evaluation indicator, and n is the total number of evaluation indicators under this evaluation dimension.

7. The method for evaluating the health of an air separation production line according to claim 1, characterized in that, In step S5, based on the scores of each evaluation dimension and the preset dimension weights, the health score of each first-level subsystem layer is calculated, including: The weighted summation method is used to calculate the health score (SubsysScore) of the first-level subsystem layer, as shown in the following formula: in, Let be the preset dimension weight of the i-th evaluation dimension under the first-level subsystem layer, and satisfy . , Let be the score of the i-th evaluation dimension layer, and m be the total number of evaluation dimension layers under the first-level subsystem layer.

8. The method for evaluating the health of an air separation production line according to claim 1, characterized in that, In step S6, the overall health evaluation result of the air separation production line is calculated and output, including: The weighted summation method was used to calculate the overall health evaluation results of the air separation production line. The formula is as follows: in, Let be the preset subsystem weights of the j-th first-level subsystem layer, and satisfy . , Let p be the health score of the j-th first-level subsystem layer, and p be the total number of first-level subsystem layers.

9. A computer device, characterized in that, The system includes a memory and a processor, wherein the memory stores computer-readable instructions that, when executed by the processor, cause the processor to perform the steps of a method for evaluating the health of an air separation production line as described in any one of claims 1 to 8.

10. A storage medium storing computer-readable instructions, characterized in that, When the computer-readable instructions are executed by one or more processors, the one or more processors perform the steps of the air separation production line health evaluation method as described in any one of claims 1 to 8.

Images