CN-122020453-A - Running state monitoring method, device, equipment and storage medium

CN122020453ACN 122020453 ACN122020453 ACN 122020453ACN-122020453-A

Abstract

The application discloses a method, a device, equipment and a storage medium for monitoring an operation state, and relates to the technical field of state monitoring. The method comprises the steps of obtaining original operation data of multiple data types of target equipment, extracting data characteristics of the original operation data in a preset time window aiming at the original operation data of each data type, wherein the time window comprises multiple time points, and combining and inputting the data characteristics of all the original operation data in the time window into a trained large model to obtain the operation state of the target equipment output by the large model.

Inventors

ZHENG NAIJIA
XIAO KAIHUA
TAN LU
WU CUIJUAN
LI JIAWEI

Assignees

中科云谷科技有限公司

Dates

Publication Date: 20260512
Application Date: 20251231

Claims (10)

1. A method of operating condition monitoring, the method comprising: Acquiring original operation data of multiple data types of target equipment; extracting data characteristics of the original operation data in a preset time window aiming at the original operation data of each data type, wherein the time window comprises a plurality of time points; And combining and inputting the data characteristics of all the original operation data in the time window into a trained large model to obtain the operation state of the target equipment output by the large model.
2. The method for monitoring an operation state according to claim 1, wherein extracting data features of the original operation data within a preset time window comprises: And extracting the instantaneous characteristics of the original operation data at each time point in the time window and/or the integral characteristics of the original operation data in the time window.
3. The operational state monitoring method of claim 2, wherein the raw operational data comprises raw agitator drum rotational speed data, raw vibration data, and raw weight data, extracting transient characteristics of the raw operational data at each point in time within the time window, and/or overall characteristics of the raw operational data within the time window, comprising: Extracting the instantaneous rotating speed and super-positive and super-negative rotating threshold conditions of the original mixing drum rotating speed data at each time point in the time window, and the average rotating speed, rotating speed variance and rotating speed change conditions of the original mixing drum rotating speed data in the time window; Extracting vibration energy, vibration peak value, vibration amplitude and frequency domain characteristics of the original vibration data in the time window; and extracting the instantaneous weight of the original weight data at each time point in the time window, and determining the average weight and the weight change condition of the original weight data in the time window based on the instantaneous weight.
4. The method of claim 1, further comprising a training step of the large model, the training step comprising: Acquiring historical operation data of multiple data types of the target equipment in different operation states; Extracting historical data characteristics of historical operation data of each data type in the time window according to each operation state; And training the large model based on the historical data characteristic combination of all the historical operation data in the time window and the corresponding operation state to obtain the trained large model.
5. The operating condition monitoring method of any one of claims 1-4, wherein the operating condition includes a plurality of steady state operating conditions, and a switching condition between different steady state operating conditions.
6. The operating condition monitoring method of claim 5, further comprising: and under the condition that the running state is the switching state between the different steady-state running states, identifying a target time point when the target equipment is switched between the different steady-state running states, and extracting the data characteristic of the target equipment at the target time point.
7. The operating condition monitoring method of claim 1, wherein the operating condition comprises an abnormal operating condition, the method further comprising: And controlling the target equipment to output prompt information under the condition that the running state is the abnormal running state.
8. An operating condition monitoring device, comprising: A memory configured to store instructions; A processor configured to invoke the instructions from the memory and when executing the instructions is capable of implementing the operating condition monitoring method according to any of claims 1 to 7.
9. An operating condition monitoring device, comprising: the operation state monitoring device according to claim 8.
10. A machine-readable storage medium having instructions stored thereon, which when executed by a processor cause the processor to be configured to perform the method of operating condition monitoring according to any of claims 1 to 7.

Description

Running state monitoring method, device, equipment and storage medium Technical Field The present application relates to the field of state monitoring technologies, and in particular, to a method, an apparatus, a device, and a storage medium for monitoring an operation state. Background In the large background of industry 4.0 and intelligent manufacturing, the requirements for efficient and reliable operation of equipment are increasing. The operation state monitoring is widely focused as a key link for guaranteeing the stable operation of equipment, realizing early warning of faults and optimizing the maintenance strategy of the equipment. Currently, equipment operating condition monitoring relies primarily on conventional sensor data and simple threshold alarm systems. Taking a mixer truck as an example, the operation state monitoring of the mixer truck usually collects data through a sensor and judges based on a preset rule, for example, when the rotation speed exceeds a certain fixed value, the mixer truck is judged to be in a working state. However, the threshold value of such methods is often fixed and difficult to adjust depending on manual experience setting. Because the actual running state of the equipment is influenced by various factors, the fixed threshold is difficult to adapt to complex and changeable working environments, false alarm or missing alarm is easy to occur, and the running state identification accuracy is low. Disclosure of Invention The embodiment of the application aims to provide an operation state monitoring method, device and equipment and a storage medium. To achieve the above object, a first aspect of the present application provides an operation state monitoring method, including: Acquiring original operation data of multiple data types of target equipment; extracting data characteristics of the original operation data in a preset time window aiming at the original operation data of each data type, wherein the time window comprises a plurality of time points; and combining and inputting the data characteristics of all the original operation data in the time window into the trained large model to obtain the operation state of the target equipment output by the large model. In the embodiment of the application, extracting the data characteristics of the original operation data in a preset time window comprises extracting the instantaneous characteristics of the original operation data at each time point in the time window and/or the integral characteristics of the original operation data in the time window. In the embodiment of the application, the original operation data comprises original stirring cylinder rotating speed data, original vibration data and original weight data, the instantaneous characteristics of the original operation data at each time point in a time window and/or the integral characteristics of the original operation data in the time window are extracted, the method comprises the steps of extracting the instantaneous rotating speed and the super forward and reverse rotation threshold condition of the original stirring cylinder rotating speed data at each time point in the time window and the average rotating speed, the rotating speed variance and the rotating speed change condition of the original stirring cylinder rotating speed data in the time window, extracting the vibration energy, the vibration peak value, the vibration amplitude and the frequency domain characteristics of the original vibration data in the time window, extracting the instantaneous weight of the original weight data at each time point in the time window and determining the average weight and the weight change condition of the original weight data in the time window based on the instantaneous weight. The method further comprises a training step of the large model, wherein the training step comprises the steps of obtaining historical operation data of multiple data types of the target equipment in different operation states, extracting historical data characteristics of the historical operation data of each data type in a time window according to each operation state, and training the large model based on the historical data characteristic combination of all the historical operation data in the time window and the corresponding operation state to obtain a trained large model. In an embodiment of the present application, the operating states include a plurality of steady state operating states, and a switching state between different steady state operating states. In the embodiment of the application, the method further comprises the steps of identifying a target time point when the target equipment is switched between different steady-state operation states under the condition that the operation state is the switching state between the different steady-state operation states, and extracting the data characteristics of the target equipment at the target time point. In the embodiment o