Method for estimating, deducing, and evaluating the sound state of industrial equipment based on a digital twin

Abstract

The present invention discloses a method for estimating, deducing, and evaluating the sound state of industrial equipment based on a digital twin. In the case of a data center infrastructure scenario (for example, an industrial Internet application scenario), although it is considered that the probabilities of failures of equipment in different environments are related to various factors, conventional solutions can only issue an alarm after a failure occurs in the equipment, and it is impossible to estimate, deduce, and evaluate the sound state of equipment that may have a failure. Therefore, they are hardly useful for prevention before a failure and cause analysis after a failure of the equipment. Accordingly, the present invention uses digital twin technology to model the equipment in the scenario, communicate the physical equipment with a digital model, and perform estimation, deduction, and evaluation based on the operating state data of the digital equipment model, thereby achieving the purpose of early warning for equipment in an abnormal operating state, improving the reliability and stability of the equipment, and ensuring the operation and safety of the data center. A solution for estimating, deducing, and evaluating the sound state of industrial equipment is proposed.

Description

Technical Field

[0001] The present invention relates to the field of digital twins, and in particular, to a method for state estimation, deduction, and evaluation in digital twins.

Background Art

[0002] A digital twin refers to constructing a "digital twin" model corresponding to an actual physical system in a virtual environment by using digital technology, and completing the simulation, analysis, and prediction of the real world through data interconnection with the actual physical system, thereby improving the operation efficiency and accuracy in the real world.

[0003] In the case of a data center infrastructure scenario (such as an industrial Internet application scenario), equipment failures have a great impact on the normal operation and business security of the data center. Therefore, the development of digital twin estimation, deduction, and evaluation technologies is very important for ensuring the reliability and stability of data center equipment and improving the operation efficiency and business security of the data center.

[0004] Conventional monitoring methods can often issue alarms only after a failure occurs in the equipment, but cannot give early warnings and detect abnormal changes in the healthy state of the equipment early. Digital twin estimation, deduction, and evaluation technologies connect physical equipment with a digital model through a communication link, construct the digital model as a virtual image of the physical equipment, and perform estimation, deduction, and evaluation based on the operation state data of the digital equipment model, thereby realizing early warnings and fault analysis for equipment in abnormal operation states. At the same time, digital twin technology can also help optimize the design and operation parameters of the equipment, improve the performance and efficiency of the equipment, and thereby reduce the energy consumption and maintenance costs of the data center.

[0005] In short, digital twin estimation, deduction, and evaluation technologies have broad application potential in early warning of equipment failures and optimization of management in data centers, can improve the reliability, stability, and operating efficiency of data centers, and can provide an important guarantee for the safe and stable operation of data centers.

Summary of the Invention

[0006] Regarding the above problems, the present invention aims to apply digital twins to data center scenarios (such as industrial Internet application scenarios) to achieve the goal of improving the reliability, stability, and operating efficiency of data centers, thereby providing a basis for the safe and stable operation of data centers, and provides a method for estimating, deducing, and evaluating the sound state of industrial equipment based on digital twins.

[0007] The method for estimating, deducing, and evaluating the sound state of industrial equipment based on digital twins has the following specific operation steps.

[0008] Step 1: In combination with digital twin technology, establish a digital virtual model for physical equipment in a data center scenario, communicate with the physical equipment, and ensure that the real-time operation state information and real-time environmental information of the physical equipment in the data center scenario are synchronized with the digital virtual model.

[0009] Step 2: Use the past operation state information and environmental information of physical equipment in a data center scenario as empirical sample data, and use the statistical histogram method to construct a state sequence (S1, S2,..., S k ) for describing different states of the operating equipment, where the service life of the equipment corresponding to each state is (d1, d2,..., d k ), and construct a state transition probability matrix P k×k and a judgment matrix X 6×4 .

[0010] Step 3: Establish a state evaluation formula that takes the operating time length L, current intensity I, and voltage level U of the device as parameters, considers environmental factors such as temperature T, humidity H, and dust quality A in the air, and results in the sound state of the device.

[0011] Step 4: Calculate the current state evaluation value Q0 of the device according to the state evaluation formula, and match the closest state in the state sequence to obtain the

Number

[0012] Step 5: Based on Q0, obtain a transition state sequence according to the state transition probability matrix, perform one round of estimation and deduction, obtain the state evaluation matrix Q1 of the first round of estimation and deduction, and obtain the corresponding state probability matrix

Number

Number

[0013] Step 6: Repeat Step 5 for estimation and deduction until the expected service life of the device is less than the safety value d s to obtain the state evaluation matrix Q num and the corresponding state probability matrix P rnum of the num-th round of estimation and deduction. For each state evaluation value in Q num match the closest state in the state sequence to obtain the

Number

[0014] Step 7: Statistically calculate the expected service life of the device throughout the entire estimation and deduction process until the estimation and deduction are completed, and the estimated

Number

[0015] Step 8, the actual

Number

[0016] Furthermore, the expressions of the state transition probability matrix P k×k and the judgment matrix X 6×4 are specifically as follows.

Number

[0017] Furthermore, the expression of the state evaluation formula in Step 3 is as follows.

Number

[0018] Furthermore, the expression of the weight w m of the mth evaluation factor is as follows.

Number

[0019] Furthermore, step 4 is specifically as follows.

Number

[0020] Furthermore, the transition state sequence of step 5 is

Number

[0021] Furthermore, the first estimated and deduced state evaluation matrix Q1 of step 5 and the corresponding state probability matrix

Number

[0022] For each state evaluation value in Q1, match the state closest in the state sequence to obtain the expected service life of the corresponding device, specifically as follows.

Number

[0023] Furthermore, the num-th estimated and deduced state evaluation matrix Q in step 6 num and the corresponding state probability matrix P rnum , for the device

Number

Number

[0024] Furthermore, the estimated and deduced

Number

[0025] Furthermore, based on the actual

Number

Number

[0026] Beneficial effects Conventional monitoring methods can often issue alarms only after a failure occurs in the device, and cannot perform early warnings and detect abnormal changes in the sound state of the device at an early stage. The digital twin estimation, deduction, and evaluation method proposed in this patent connects the physical device with a digital model through a communication link, constructs the digital model as a virtual image of the physical device, and performs estimation, deduction, and evaluation based on the operating state data of the digital device model, thereby realizing early warnings and fault analysis for devices with abnormal operating states.

Brief Description of the Drawings

[0027]

Figure 1

Embodiments for Carrying Out the Invention

[0028] The technical solution of the present invention will be further described below by combining the drawings and specific embodiments.

[0029] As shown in FIG. 1, the method for estimating, deducing, and evaluating the sound state of industrial equipment based on digital twins has the following specific operation steps.

[0030] Step S101: In combination with digital twin technology, establish a digital virtual model for the physical devices in the data center scenario (for example, the industrial Internet application scenario), communicate and interact with the physical devices, and ensure that the real-time operation state information and real-time environment information of the physical devices in the data center scenario are synchronized with the digital virtual model.

[0031] First, model the devices in the data center scenario so that the physical characteristics and operating conditions of the model are consistent with the physical devices. Next, collect the real-time data of the environment and devices by sensors, convert the data into digital format, and perform data interaction with the digital virtual model. Then, fuse the mathematical model and the real-time data converted into digital format to establish a digital twin model.

[0032] Step S102: Use the statistical histogram method for empirical sample data (the past operating state information and environmental data of the devices) to construct a state sequence (S1, S2,..., S k ) for describing different states of the operating devices, and S krefers to the k-th state of the device in operation. For one device, there is a gradual evolution process from a sound state to an abnormal state prone to failure. This process is divided into k states, and there is a service life for the device corresponding to each of these k states. The service life sequence of the device (d1, d2,..., d k ) forms a state transition probability matrix P k×k and a judgment matrix X 6×4 to describe the state transition relationship of the device. In the judgment matrix, three internal influencing factors of the device (the operating time length L of the device, the current intensity I of the device, the voltage level U of the device) and three external environmental influencing factors (temperature T, humidity H, the quality A of dust in the air) are considered. Each influencing factor is divided into four levels: [none, low, medium, high] according to the degree of influence.

[0033]

Number

[0034] Step S103: By monitoring the internal influencing factors of the device in the digital virtual model in real time, using the operating time length L of the device, the current intensity I of the device, and the voltage level U of the device as parameters, considering the environmental influencing factors of temperature T, humidity H, and the quality A of dust in the air, establish a state evaluation formula with the sound state of the device as the result. Obtain the current state evaluation value Q0 of the device according to this formula, match the closest state in the state sequence, and obtain the corresponding

Number

[0035]

Number

[0036] The weight w of the m-th evaluation factor m is obtained from the judgment matrix X 6×4 by the entropy weight method.

Number

[0037] Based on the information entropy of the internal state influence factors of each device, the corresponding weight w m is calculated.

Number

[0038] Based on the obtained Q0, find the state closest in the complete state sequence, and for the device corresponding to this state

Number

Number

[0039] Step S104, based on Q0, obtain the transition state sequence of the device according to the state transition probability matrix

Number

[0040]

Number

[0041]

Number

[0042]

Number

[0043] Step S105, repeat Step S104 for estimation and deduction until the expected service life of the device is smaller than the safety value d s and perform estimation and deduction according to the following tree-branch structure estimation and deduction formula for the 1×k num state evaluation matrix Q num of the device deduced for the num-th time and the corresponding 1×k num state probability matrix P rnum to obtain Q num , and for each state evaluation value in Q, find the state closest to the complete state sequence and the

Number

[0044]

Number

[0045] Each time of presumption and deduction yields the expected service life of a device. Considering the probabilistic factors, the more times of presumption and deduction of the expected service life of this device, the smaller it becomes. Therefore, it will surely be smaller than the safety value. At this time, the final number of times of presumption and deduction is obtained. num is any time of presumption and deduction in the process until the presumption and deduction terminate, and Num is the number of times of presumption and deduction when it terminates.

[0046] Step 106: Calculate the total expected service life of the device in the presumption and deduction process until the presumption and deduction end, and the deduced

Number

Number

[0047] Step S107: Based on the actual

Number

Number

[0048] The description of the above embodiments is for helping to understand the method of this application and its core idea. However, for those skilled in the art, on the premise of not departing from the principle of this application, several improvements and modifications can also be made to this application. It should be pointed out that these improvements and modifications are also included within the protection scope of the claims of this application.

Claims

1. A method for estimating, deducing, and evaluating the sound state of industrial equipment based on a digital twin, The specific steps of this method are as follows: Step 1: In combination with digital twin technology, establish a digital virtual model for physical equipment in a data center scenario, communicate and interact with the physical equipment, and ensure that the real-time operation status information and real-time environmental information of the physical equipment in the data center scenario are synchronized with the digital virtual model. Step 2: Use the past operating state information and environmental information of physical devices in the data center scenario as empirical sample data, and use the statistical histogram method to construct a state sequence (S １ , S ２ ,..., S ｋ ), where S ｋ represents the k-th state of the device in operation, the corresponding device lifespan sequence is (d １ , d ２ ,..., d ｋ ), and construct a state transition probability matrix P ｋ×ｋ and a judgment matrix X ６×４ . Step 3: Using the operating time length L of the equipment, the current intensity I of the equipment, and the voltage level U of the equipment as parameters, considering environmental factors such as temperature T, humidity H, and the quality A of dust in the air, establish a state evaluation formula with the sound state of the equipment as the result. Step 4. Calculate the current device state evaluation value Q according to the state evaluation formula, and match the closest state in the state sequence to obtain the corresponding device's ０ by calculating and matching the closest state in the state sequence 【Number 36】 to obtain Step 5, Q ０ Based on ０ , obtain a transition state sequence according to the state transition probability matrix, perform one-time estimation and deduction, and obtain the state evaluation matrix Q １ obtained from the first estimation and deduction, and the corresponding state probability matrix 【No. 37】 Obtained, Q １ For each state evaluation value among them, match the state closest in the state sequence, and for the corresponding device 【No. 38】 to obtain Step 6: Repeat Step 5 until the expected service life of the device becomes less than the safety value d ｓ and repeat the estimation and deduction. Obtain the state evaluation matrix Q ｎｕｍ estimated and deduced for the num-th time, and the corresponding state probability matrix P ｒｎｕｍ . For each state evaluation value in Q ｎｕｍ , match the state closest in the state sequence, and for the corresponding device 【Number 39】 to obtain Step 7: Statistically calculate the expected service life of the equipment throughout the entire estimation and deduction process until the estimation and deduction are completed, and the estimated and deduced 【Number 40】 to obtain Step 8: Based on the actual 【Number 41】 of the equipment, feedback and correct the state evaluation matrix. A method for estimating, deducing, and evaluating the sound state of industrial equipment based on a digital twin.

2. State transition probability matrix P of step 2 ｋ×ｋ and judgment matrix X ６×４ The expression of is specifically as follows: 【Number 42】 Xmn indicates that the m-th evaluation factor is at the n-th level. The evaluation factors are L, I, U, T, H, and A respectively. The evaluation levels include four levels: [none, low, medium, high]. It is characterized in that 1 ≤ m ≤ 6 and 1 ≤ n ≤ 4. The method for estimating, deducing, and evaluating the sound state of industrial equipment based on a digital twin according to Claim 1.

3. The expression of the state evaluation formula in Step 3 is as follows: 【Number 43】 Here, (A １ , A ２ , A ３ , A ４ , A ５ , A ６ ) = (L, I, U, T, H, A), D is the distance between the device and the safety line, and D ｈ and D ｌ are the safety upper limit and lower limit, μ ｍ is the expected safety value of the m-th evaluation factor, K １ is the amplification factor, w ｍ is the weight of the m-th evaluation factor, and the evaluation factors are L, I, U, T, H, and A respectively. The method for estimating, deducing, and evaluating the sound state of an industrial device based on the digital twin according to claim 1 is characterized in that.

4. The weight w of the m-th evaluation factor ｍ has the following expression: 【Number 44】 Here, m = 1, 2, ..., 6, n = 1, 2, ..., 4, X ｍｎ indicates that the m-th evaluation factor is at the n-th level, the evaluation factors are L, I, U, T, H, A respectively, and the evaluation levels include four levels of [none, low, medium, high]. A method for estimating, deducing, and evaluating the sound state of industrial equipment based on the digital twin according to claim 1, characterized in that it is as described above.

5. Step 4 is specifically as follows: 【Number 45】 Here, r0 is the state number closest to Q that is matched in the state sequence. ０ The method for estimating, deducing, and evaluating the soundness state of industrial equipment based on a digital twin according to claim 1, characterized in that r0 is the state number closest to Q that is matched in the state sequence.

6. The transition state sequence in Step 5 is 【Number 46】 State transition probability matrix P ｋ×ｋ which is the r0-th row, where r0 is the state number closest to Q ０ in the state sequence that is matched, for the method for estimating, deducing, and evaluating the sound state of industrial equipment based on a digital twin according to claim 1.

7. The first estimated / deduced state evaluation matrix Q in step 5 １ and the corresponding state probability matrix 【Number 47】 Here, τ(1) represents the first randomly taken value of the oscillation function τ, and τ is an oscillation function that follows a Gaussian distribution τ ~ N(μ, σ ２ ), where μ and σ ２ are the mean value and expected variance of this oscillation function, respectively, Q １ For each of the state evaluation values among them, match the state closest in the state sequence to obtain the expected service life of the corresponding device. Specifically, it is as follows: 【Number 48】 It is characterized in that it is the transpose of

8. The n-th estimated and deduced state evaluation matrix Q of step 6 ｎｕｍ and the corresponding state probability matrix P ｒｎｕｍ , of the device 【Number 49】 is specifically as follows: 【Number 50】 It is characterized in that it is the threshold of the service life of the equipment. The method for estimating, deducing, and evaluating the sound state of industrial equipment based on a digital twin according to Claim 1.

9. The estimated and deduced 【Number 51】 in Step 6. Here, NUM is the total number of estimations and deductions performed until the estimation and deduction are completed. The method for estimating, deducing, and evaluating the sound state of industrial equipment based on a digital twin according to Claim 1.

10. The actual 【Number 52】 Based on the above, according to the following formula, the threshold value d of the equipment's service life ｔｈ is updated to achieve feedback and correction for the state evaluation matrix: 【Number 53】 The method for estimating, deducing, and evaluating the soundness state of industrial equipment based on the digital twin according to claim 1, characterized in that it is the threshold value of the service life of the updated equipment.

Images