Method, system, electronic device and computer storage medium for managing a dehumidification device

Abstract

The application discloses a kind of management method, system, electronic equipment and computer storage medium of dehumidification device, overcome the problem that the evaluation parameter of dehumidification device in prior art is not detailed enough, not enough, resulting in evaluation result is not accurate enough, method includes: obtaining the first historical data and second historical data of dehumidification device;Establish digital twin model and optimization;The first real-time data of the dehumidification device is collected, and it is input to the optimized digital twin model, and second real-time data is obtained;The first real-time data and the second real-time data are received, and the performance of the dehumidification device is evaluated and whether the dehumidification device is abnormal is judged from this;If abnormal, carry out abnormal alarm and fault diagnosis.Can carry out performance evaluation and fault diagnosis to dehumidification device and each key equipment in dehumidification device, have more, more comprehensive data for judging fault reason, make fault diagnosis more accurate.

Description

Technical Field

[0001] This invention relates to the field of dehumidification device management and control technology, and in particular to a management method, system, electronic device, and computer storage medium for a dehumidification device. Background Technology

[0002] Dehumidifiers are widely used in situations where environmental humidity requirements are strict. Therefore, it is necessary to strictly control the performance of dehumidifiers to ensure their normal operation and thus ensure that the environmental humidity meets the standards.

[0003] However, the existing technology mainly focuses on monitoring and evaluating some easily measurable operating data during the operation of dehumidifiers. It lacks monitoring and evaluation of other operating data of dehumidifiers that are difficult to measure or costly to measure, as well as their own performance parameters. This results in the inability to achieve comprehensive health management of dehumidifiers, affecting their working performance and efficiency. For example: (1) There is a lack of performance data evaluation of each device in the dehumidifier and the overall performance data evaluation of the dehumidifier, which makes it impossible for maintenance personnel to fully and timely understand the current operating performance of the dehumidifier. (2) The existing abnormal diagnosis basis is only daily monitoring data, which is prone to missed diagnosis, large diagnostic errors, and low diagnostic accuracy. (3) There is a lack of abnormal cause analysis. The abnormal diagnosis results cannot determine the cause of abnormality or failure, which makes it impossible for maintenance personnel to deal with abnormalities or failures in a targeted manner. Summary of the Invention

[0004] The purpose of this invention is to overcome the problem that the evaluation parameters of dehumidification devices in the prior art are not detailed or numerous enough, resulting in inaccurate and incomplete evaluation results. This invention provides a management method, system, electronic device and computer storage medium for dehumidification devices, which can perform performance evaluation and fault diagnosis on dehumidification devices and their key components. It provides more comprehensive data to determine the cause of faults, making fault diagnosis more accurate.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A method for managing a dehumidifier includes the following steps:

[0007] S1: Obtain the first and second historical data of the dehumidifier;

[0008] S2: Establish a digital twin model and optimize the digital twin model based on the first historical data and the second historical data;

[0009] S3: Collect the first real-time data of the dehumidification device and input the first real-time data into the optimized digital twin model. The optimized digital twin model calculates the second real-time data based on the first real-time data.

[0010] S4: Receive the first real-time data and the second real-time data, evaluate the performance of the dehumidification device based on the first real-time data and the second real-time data, and determine whether the dehumidification device has malfunctioned.

[0011] S5: If an abnormality occurs, an abnormality alarm and fault diagnosis will be performed.

[0012] A digital twin model is a model obtained using digital twin technology. Digital twin technology refers to the creation of a digital virtual model of an equipment object using its mechanistic model (including its design principles, working principles, technological processes, and other physical models) and historical operating data. Performance evaluation assesses the performance of each key component in a dehumidifier and, based on the operating performance indicators of each component, comprehensively obtains the overall performance evaluation of the dehumidifier. Anomaly alarms and fault diagnosis utilize all data in the digital twin model (including measured and calculated data) for anomaly alarms, and fault diagnosis may also require the use of all data in the model.

[0013] The present invention first establishes a digital twin model, which corresponds to the dehumidification device as a whole, including digital twin models of each device, and then optimizes the digital twin model based on the acquired first historical data and second historical data.

[0014] After optimizing the digital twin model, digital twin model calculations are performed. Specifically: First, the first real-time data of the dehumidification device is collected. This first real-time data consists of measurable data from the dehumidification device, such as motor current and speed in the motor unit; fan speed, flow rate, and pressure in the fan unit; and air temperature and humidity, as well as ambient temperature and humidity, in the rotary drum unit. Using the optimized digital twin model, the collected first real-time data is input into the corresponding device digital twin model to obtain the second real-time data. The second real-time data consists of data from the dehumidification device that is difficult to measure, such as motor torque, power, and efficiency in the motor unit; fan efficiency in the fan unit; and the moisture adsorption capacity of the rotary drum unit.

[0015] After obtaining the calculation results from the digital twin model, performance evaluation, anomaly alarms, and fault diagnosis are performed, and alarms are triggered. Specifically: using the obtained first real-time data and second real-time data, the performance of each device in the dehumidification unit and the entire dehumidification unit is evaluated, and it is determined whether any anomalies have occurred, and an alarm is triggered when an anomaly occurs.

[0016] Data collection must be real-time; real-time performance is a key aspect of digital twin models. A highlight of digital twin models is their ability to calculate other missing data from limited measurement data. This advantage allows the model to more comprehensively reflect the object's information. All this measured and calculated information can be utilized in performance evaluation, anomaly alarms, and fault diagnosis, thereby improving the effectiveness of these functions. Simultaneously, through performance evaluation, anomaly alarms, and fault diagnosis, maintenance personnel can promptly understand the health status of the dehumidifier. When performance degradation, abnormal phenomena, or equipment failures occur, they can promptly designate or modify operating and maintenance plans, ensuring long-term stable and compliant temperature and humidity within the space (room, workshop) controlled by the dehumidifier; or, in the event of anomalies, quickly return to the set range, thus minimizing losses caused by abnormal temperature and humidity.

[0017] Preferably, step S1 includes the following specific steps:

[0018] S1.1: Measure and record the historical operating data of the dehumidifier;

[0019] S1.2: Obtain historical operation data from measurement records, and process the historical operation data to obtain the first historical data and the second historical data.

[0020] The measured historical operating data includes the temperature and humidity at various key locations in the dehumidifier's piping, the temperature and humidity within the controlled space, the opening degree of each valve in the dehumidifier, the rotation speed of the dehumidifier impeller, and the temperature and vibration of each bearing in the fan and motor of the dehumidifier, etc.

[0021] Preferably, step S2 specifically includes:

[0022] S2.1: Map the equipment components, topology, connection relationships, control logic, and physical rules of the dehumidification device to construct physical equations and form a digital twin model;

[0023] S2.2: Input the first historical data into the digital twin model, and the digital twin model calculates the first theoretical data based on the first historical data;

[0024] S2.3: Optimize the digital twin model based on the first theoretical data and the second historical data.

[0025] A digital twin model can reflect the entire lifecycle of a corresponding device entity. This invention first fully understands the physical models of the dehumidification device, including its design principles, working principles, and the physical changes in the external environment caused by the device's operation, and then establishes corresponding mathematical models. The digital twin model primarily uses mechanistic modeling. For example, the mass flow rate is calculated based on the average flow velocity. The relevant mapping relationship in this digital twin model is: Mass flow rate = Medium density * Average flow velocity * Pipe cross-sectional area. Then, using first and second historical data, the parameters of the digital twin model are tuned to obtain an optimized digital twin model. During optimization, the first historical data (such as average flow velocity) is input into the established digital twin model to obtain the first theoretical data (such as the theoretical value of mass flow rate). The second historical data is the actual value corresponding to the first theoretical data (such as the actual value of mass flow rate) obtained from measurements recorded during actual operation. By comparing the first theoretical data and the second historical data (such as the theoretical and actual values ​​of mass flow rate), the error between the actual and theoretical values ​​is obtained, and then the digital twin model is corrected.

[0026] This invention, based on the digital twin model of a single device, can also establish a device-level digital twin model. A real dehumidifier often contains multiple devices with different functions. These devices are combined through a certain topological structure and interact with each other or with the environment in a specific way to achieve the overall function of the dehumidifier. The same principle applies to establishing device-level object models using digital twin technology. First, different device digital twin models are established using digital twin technology. Then, based on the interaction mechanisms between the devices, the device-level digital twin models are combined to establish a device-level digital twin model of the dehumidifier.

[0027] This invention analyzes and models the design and operating principles of various devices and components in a dehumidification device. Simultaneously, it utilizes first and second historical data to tune the parameters of the established digital twin model, resulting in an optimized digital twin model. This enables performance evaluation and fault diagnosis of the dehumidification device and its key components. More comprehensive data is available to determine the cause of faults, making fault diagnosis more accurate and saving manpower required for dehumidification device maintenance. The key components include fans, motors, and impellers.

[0028] Preferably, step S4, which involves evaluating the performance of the dehumidifier based on the first real-time data and the second real-time data and determining whether the dehumidifier has malfunctioned, specifically includes:

[0029] The method involves determining whether the first real-time data meets a first threshold and / or whether the second real-time data meets a second threshold and / or whether the correlated calculated value of the first and second real-time data meets a third threshold; wherein the first threshold, the second threshold, and the third threshold are reference values ​​for ensuring the dehumidification device meets performance standards. This is merely a preferred method of determination in this invention and does not imply that this method is the only viable method in the invention.

[0030] Preferably, step S4 specifically includes: if an anomaly occurs, issuing an anomaly alarm, and performing fault diagnosis based on the first real-time data and the second real-time data at the time of the anomaly alarm. The alarm method can be a threshold alarm or an expert strategy alarm; using data at the time of the anomaly for fault diagnosis results in more accurate diagnosis.

[0031] Preferably, step S4 also includes displaying an abnormal alarm indicator and the cause of the fault. This allows maintenance personnel to clearly identify the specific fault and respond promptly and effectively, improving efficiency.

[0032] A management system for a dehumidification device includes:

[0033] The data acquisition module is used to acquire the first and second historical data of the dehumidifier.

[0034] A model building module is used to build a digital twin model and optimize the digital twin model based on the first historical data and the second historical data.

[0035] The data acquisition module is used to acquire the first real-time data of the dehumidification device and input the first real-time data into the optimized digital twin model. The optimized digital twin model calculates the second real-time data based on the first real-time data.

[0036] The evaluation module receives the first real-time data and the second real-time data, evaluates the performance of the dehumidification device based on the first real-time data and the second real-time data, and determines whether the dehumidification device is malfunctioning.

[0037] The interaction module is used to perform corresponding operations based on the abnormal alarms and fault diagnosis prompts from the evaluation module.

[0038] This invention utilizes digital twin technology to establish corresponding digital twin models for each device and component in a dehumidifier, and also establishes a device-level digital twin model. It can calculate the performance indicators of each device and the entire dehumidifier, obtaining performance evaluation results. Furthermore, it can calculate other missing data within the dehumidifier using limited measurement data, enabling health monitoring and anomaly alarms for these missing data points. This allows the anomaly alarm function to cover more comprehensive factors. Simultaneously, when a malfunction occurs in the dehumidifier, more comprehensive data is available to determine the cause of the malfunction, making fault diagnosis more accurate.

[0039] Preferably, the data acquisition module further includes:

[0040] The display module, connected to the interaction module, is used to display abnormal alarm indicators and the cause of the fault. This allows maintenance personnel to clearly understand the specific fault and respond promptly and effectively, improving efficiency.

[0041] Preferably, the data acquisition module includes:

[0042] The sensor module includes several sensors that measure key operating data, process data, and environmental data of the dehumidifier in real time and send them to the data acquisition device. Each data point required by the dehumidifier corresponds to one output data of the sensor, such as the supply air temperature. A sensor device can measure one or more data points, such as a temperature and humidity integrated sensor. It can simultaneously measure the temperature and humidity at a physical location and generate two data points.

[0043] The data acquisition device collects data from the sensor and converts the continuous measurement results of the sensor into periodic discrete data and sends it to the data transmission device. The period can be adjusted according to the algorithm requirements or other circumstances. Usually, one sensor device is equipped with one data acquisition device, or multiple sensor devices can share one data acquisition device.

[0044] Data transmission equipment, including lines, gateways, and routing devices, is used to receive data sent by data acquisition devices and transmit the received data to the model building module. Typically, data acquisition devices within the same physical space can share a set of data transmission equipment, depending on the conditions of the actual physical space.

[0045] This invention requires real-time measurement of key operating data, process data, and environmental data of the dehumidification device, such as the temperature and humidity at various key locations in the dehumidification device's pipeline, the temperature and humidity in the space controlled by the dehumidification device, the opening degree of each valve in the dehumidification device, the rotation speed of the dehumidification impeller, and the temperature and vibration of each bearing of the fan and motor in the dehumidification device. These data need to be measured by corresponding sensors.

[0046] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it causes the electronic device to implement the steps of the management method for the dehumidification device. This is used to implement the management method for the dehumidification device.

[0047] A computer storage medium storing a computer program, which, when executed on an electronic device, implements the steps of the management method for the dehumidification device.

[0048] Therefore, the present invention has the following beneficial effects:

[0049] 1. It can calculate the performance indicators of each device in the dehumidification system and the entire dehumidification system, obtain performance evaluation results, and enable equipment operation and maintenance personnel to understand the performance of the equipment and the health status of the equipment and dehumidification system;

[0050] 2. It can calculate other missing data in the dehumidifier from the limited measurement data in the dehumidifier, and then perform health monitoring and abnormal alarms on these missing data, so that the abnormal alarm function covers more comprehensive factors. At the same time, when the dehumidifier malfunctions, there is more and more comprehensive data to determine the cause of the malfunction, making the fault diagnosis more accurate.

[0051] 3. Remote data access replaces on-site patrols, reducing the manpower required for control rooms or data centers;

[0052] 4. When the dehumidifier experiences performance degradation, abnormal phenomena, or equipment failure, it can promptly designate or modify operation and maintenance plans to ensure that the temperature and humidity in the space (room, workshop) controlled by the dehumidifier remain stable and meet requirements for a long period of time, or return to the set range as soon as possible after an abnormality occurs, thereby reducing losses caused by abnormal temperature and humidity. Attached Figure Description

[0053] Figure 1 This is a flowchart of the management method of the dehumidification device of the present invention;

[0054] Figure 2 This is a schematic diagram of a rotary dehumidifier.

[0055] Figure 3 This is a schematic diagram illustrating a case where the central valve fails to operate.

[0056] Figure 4 This is a schematic diagram of the architecture of the management system of the dehumidification device of the present invention;

[0057] In the diagram: 1. Data acquisition module; 2. Model building module; 3. Evaluation module; 4. Interaction module; 5. Opening degree of the middle chilled water valve; 6. Temperature of the front duct; 7. Humidity of the front duct; 8. Temperature of the middle duct; 9. Humidity of the middle duct; 10. Temperature of the return air duct; 11. Humidity of the return air duct; 12. Data acquisition module. Detailed Implementation

[0058] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments:

[0059] Example 1:

[0060] This embodiment describes a management method for a dehumidification device, such as... Figure 1 As shown, the process includes the following steps: Step 1, acquiring first and second historical data of the dehumidifier; Step 2, establishing a digital twin model and optimizing the digital twin model based on the first and second historical data; Step 3, collecting first real-time data of the dehumidifier and inputting the first real-time data into the optimized digital twin model, which then calculates second real-time data based on the first real-time data; Step 4, receiving the first and second real-time data and evaluating the performance of the dehumidifier based on the first and second real-time data, and determining whether the dehumidifier has malfunctioned; Step 5, if an malfunction occurs, triggering an alarm and performing fault diagnosis. This embodiment establishes and optimizes a digital twin model of the dehumidifier using historical operating data under normal operating conditions. Then, using the optimized digital twin model, it calculates other data lacking measurement (i.e., second real-time data) from limited measurement data (i.e., first real-time data), providing a more comprehensive reflection of the object's information. All this measured and calculated information can be utilized in performance evaluation, alarm functions, and fault diagnosis, thereby improving the effectiveness of these functions. Meanwhile, through performance evaluation, abnormal alarm, and fault diagnosis functions, maintenance personnel can promptly understand the health status of the dehumidifier. When performance degradation, abnormal phenomena, or equipment failure occur, they can promptly designate or change operation and maintenance plans to ensure that the temperature and humidity in the space (room, workshop) controlled by the dehumidifier remain stable and meet requirements in the long term; or return to the set range as soon as possible after an abnormality occurs, thereby reducing losses caused by abnormal temperature and humidity.

[0061] Specifically, this manifests as follows:

[0062] Step 1: Obtain the first and second historical data of the dehumidifier.

[0063] The historical operating data of the dehumidification device is measured and recorded. The historical operating data includes the operating data, process data and environmental data of the dehumidification device. Specifically, it includes the temperature and humidity at various key locations in the dehumidification system pipeline, the temperature and humidity in the controlled space, the opening degree of each valve in the dehumidification device, the speed of the dehumidification impeller, the temperature and vibration of each bearing of the fan and motor in the dehumidification device, etc.

[0064] The acquired historical operating data undergoes data processing. Methods for data processing include, but are not limited to, standardizing and normalizing the historical operating data to obtain discrete first and second historical data. It should be noted that all historical operating data is measured and acquired when the dehumidifier is operating normally. For example, the power, voltage, and current data of a motor in the dehumidifier are measured and acquired. This data is then processed, and the processed voltage and current data are used as the first historical data, while the processed power data is used as the second historical data. Furthermore, they satisfy the relationship: Power = Voltage * Current.

[0065] Step 2: Establish a digital twin model and optimize the digital twin model based on the first historical data and the second historical data.

[0066] Specifically, when establishing a digital twin model of a dehumidifier, the equipment components, topology, connection relationships, control logic, and physical rules of the physical dehumidifier are mapped to construct physical equations, forming a digital twin model. Different devices have different physical mechanisms, and the physical principles used in modeling vary, including but not limited to Newton's laws, thermodynamics, and electromagnetic induction. For example, the physical relationships between the front duct, return air duct, middle chilled water coil and valves, and the middle ductwork include heat transfer and mass transfer relationships. It should be noted that in this embodiment, when establishing a digital twin model based on the dehumidifier, the method adopted is to first establish a digital twin model for each device within the dehumidifier, and then establish a digital twin model of the entire dehumidifier based on its connection methods, control logic, etc.

[0067] As described above, the established digital twin model includes various data mapping relationships. Specifically, when optimizing the digital twin model based on the first historical data and the second historical data, the first historical data is input into the digital twin model. The digital twin model calculates the first theoretical data based on the mapping relationship satisfied by the first historical data. Then, by comparing the first theoretical data and the second historical data, the coefficients of their corresponding mapping relationships are corrected, making the first theoretical data closer to or equal to the second historical data.

[0068] It should be noted that, in this embodiment, the optimization of the digital twin model can be performed simultaneously with the establishment of the digital twin model. Specifically, after each device digital twin model is established, it can be optimized using its corresponding first and second historical data. For example, as mentioned above, the mapping relationship between voltage data, current data, and power data in the digital twin model of a motor in a dehumidifier is power = k1 * voltage * current. During optimization, the voltage and current data obtained from historical operation measurements are input into the motor device digital twin model as the first historical data. The motor device digital twin model will calculate and output theoretical power data as the first theoretical data based on its mapping relationship. Then, the first theoretical data is compared with the power data obtained from historical operation measurements as the second historical data, and the coefficient k1 is corrected so that the theoretical power data is equal to or close to the power data obtained from historical operation measurements. Similarly, based on other types of first and second historical data, the parameters of the digital twin models of other devices in the digital twin model are corrected and optimized. Then, based on the optimized digital twin models of each device, a digital twin model of the dehumidification device as a whole is established. Finally, based on the first and second historical data related to the overall operation of the dehumidification device, the overall digital twin model of the dehumidification device is corrected and optimized. In another embodiment, a digital twin model of the dehumidification device as a whole can be established first, and then the parameters of the overall digital twin model of the dehumidification device can be optimized, with the same optimization principle as above.

[0069] The key feature of this invention is the use of digital twin technology. Digital twin technology has significant advantages when the amount of object data is small and the amount of abnormal or faulty sample data is limited (compared to machine learning technology, which requires a large amount of data and samples for model training). It is a modeling method that is primarily based on mechanistic models and physical principles, with operational data as an auxiliary tool.

[0070] For example, in this embodiment, the established equipment digital twin models include digital twin models of motor equipment, digital twin models of fan equipment, digital twin models of dehumidifier rotor, digital twin models of valves, digital twin models of pipelines, digital twin models of heat exchange coils, and other equipment digital twin models.

[0071] Step 3: Collect the first real-time data of the dehumidification device and input the first real-time data into the optimized digital twin model. The optimized digital twin model calculates the second real-time data based on the first real-time data.

[0072] Real-time operating data or set parameters of the dehumidification device are collected and processed to convert them into discrete first real-time data. This first real-time data is then input into an optimized digital twin model. The optimized digital twin model calculates second real-time data based on the first real-time data and a corresponding mapping relationship. For example, in a specific application, motor design parameters, real-time motor current, and speed are used as the first real-time data input into the digital twin model. The digital twin model calculates second real-time data including motor torque, power, and efficiency based on the corresponding mapping relationship. Similarly, fan design parameters, real-time fan speed, flow rate, pressure, and power are used as the first real-time data input into the digital twin model. The digital twin model calculates second real-time data including fan efficiency based on the corresponding mapping relationship. Furthermore, impeller design parameters and impeller airflow are used as the first real-time data input into the digital twin model. The digital twin model calculates second real-time data including the impeller's moisture adsorption capacity based on the corresponding mapping relationship.

[0073] Step 4: Receive the first real-time data and the second real-time data, evaluate the performance of the dehumidification device based on the first real-time data and the second real-time data, and determine whether the dehumidification device has malfunctioned.

[0074] The criteria for determining whether an anomaly has occurred vary. A single digital twin model may have multiple methods for determining whether an anomaly has occurred, and different digital twin models may also have different methods for determining whether an anomaly has occurred.

[0075] Specifically, the judgment criteria in this embodiment include, but are not limited to: judging whether the first real-time data meets the first threshold and / or whether the second real-time data meets the second threshold and / or whether the related calculation value of the first real-time data and the second real-time data meets the third threshold; wherein, the first threshold, the second threshold and the third threshold are reference values ​​for the dehumidification device to meet the working performance standards.

[0076] Specifically, the performance evaluation function assesses the current operating performance of the dehumidifier based on the first and second real-time data, enabling maintenance personnel to understand the dehumidifier's performance status and providing a reference for whether to change the dehumidifier's operating plan. The dehumidifier performance evaluation includes the performance evaluation of each key component and the overall performance evaluation of the dehumidifier.

[0077] Specifically, for example:

[0078] The performance evaluation of the motor equipment in the dehumidification device is mainly carried out by evaluating the motor's operating performance through motor design parameters, motor characteristic curves, real-time operating data such as motor current and speed or set parameter data, as well as motor efficiency, torque, power and other data calculated and output by the aforementioned digital twin model.

[0079] The performance evaluation of the fan equipment in the dehumidification device is mainly carried out by evaluating the fan's operating performance through the fan design parameters, fan performance curves, real-time operating or set parameter data such as fan speed, flow rate, pressure, and power, as well as the fan efficiency calculated using the aforementioned digital twin model.

[0080] The performance evaluation of the dehumidification impeller in the dehumidification device is mainly carried out by evaluating the impeller's design parameters, operating parameters, airflow parameters, environmental parameters, real-time operating or set parameters, as well as the impeller's moisture adsorption capacity calculated using the aforementioned digital twin model.

[0081] In addition, the performance of equipment such as valves, pipes, and heat exchange coils in the dehumidification device can be evaluated by real-time operation or setting parameters, as well as by using data related to the above data calculated and output by the aforementioned digital twin model.

[0082] The overall performance of a dehumidifier can be evaluated by combining the above-mentioned performance evaluation parameters with the overall operating data of the dehumidifier.

[0083] Step 5: If an abnormality occurs, trigger an alarm and perform fault diagnosis.

[0084] The abnormal alarm and fault diagnosis function provides alarms and cause analysis for abnormal data from the dehumidifier. After an anomaly occurs, fault diagnosis is performed based on the first and second real-time data at the time of the alarm. More precisely, after an anomaly occurs, historical operating data for a period prior to that time is acquired and combined with the first and second real-time data at that moment for fault diagnosis. After fault diagnosis is completed, an alarm icon is displayed on the terminal device to alert maintenance personnel to the abnormal situation and to display the cause of the fault. Fault causes include various equipment anomalies and corresponding operational data anomalies, helping maintenance personnel efficiently troubleshoot specific fault causes and perform targeted fault repairs. The terminal devices include, but are not limited to, smartphones, tablets, laptops, and wearable devices, facilitating remote monitoring of the dehumidifier's operation by maintenance personnel.

[0085] The following specific examples further illustrate the technical solution and effects of this method.

[0086] Taking a fault in a dual-rotor dehumidifier in the existing technology: the central chilled water valve does not operate as an example, such as... Figure 2 As shown, each number represents a data point.

[0087] Judgment process:

[0088] First, based on the design parameters, working principles, operational data, process data, and environmental data of the central chilled water coil and its valves, a digital twin model of the central chilled water coil and its valves is established. Then, based on the design parameters, working principles, operational data, process data, and environmental data of the front duct, central duct, and return air duct, digital twin models of the front duct, central duct, and return air duct are established respectively, and the parameters of these digital twin models are optimized. Next, based on the physical relationships (including heat transfer relationships, mass transfer relationships, etc.) between the front duct, return air duct, central chilled water coil and its valves, and the central duct itself, a digital twin model with the central chilled water coil as the core is established based on the digital twin models of the above-mentioned equipment.

[0089] In practical applications, first real-time data is collected from the chilled water coil, valves, and ductwork. This collected first real-time data is then input into a digital twin model to obtain corresponding second real-time data. Based on the first and second real-time data, the performance of the chilled water coil, valves, and ductwork is evaluated. Specifically, Figure 2 The real-time operating data or set parameters of sections 5 to 11 are input into the above digital twin model. The digital twin model will calculate and obtain data such as the heat exchange in the middle section and the opening degree of the middle section chilled water valve, which are difficult to measure and obtain, based on the input data and its corresponding mapping relationship.

[0090] Finally, the operating performance of the dual-rotor dehumidifier is evaluated and fault diagnosis is performed based on real-time operating data or set parameters, as well as data obtained through a digital twin model (such as the opening degree of the central chilled water valve). For example, if the obtained opening degree of the central chilled water valve differs significantly from the preset threshold for the central chilled water valve opening that satisfies the operating performance of the dual-rotor dehumidifier, a fault is determined to be a failure of the central chilled water valve to operate, an abnormal alarm is issued, and the alarm symbol and fault cause are displayed.

[0091] Figure 3 This data represents a case of a central valve malfunction occurring on a specific day. The horizontal axis represents the date and time, and the vertical axis represents the valve opening degree (%). The central valve opening degree (set) is the preset threshold that meets the operating performance requirements of the dual-rotor dehumidifier, while the central valve opening degree (calculated) is the opening degree calculated using a digital twin model. It is evident that after the malfunction occurs, the calculated central valve opening degree deviates significantly from the preset central valve opening degree, meaning the actual valve opening degree fails to meet the system's preset value. Therefore, a valve malfunction is identified.

[0092] This invention utilizes digital twin technology to obtain second real-time data based on first real-time data collected by the dehumidifier. It then uses this data to generate alarms and diagnose faults in the dehumidifier. Furthermore, it can perform fault diagnosis by combining and analyzing the first and second real-time data after any anomaly occurs. By providing performance evaluation, alarm, and fault diagnosis functions at the level of key equipment and devices, this invention allows maintenance personnel to promptly understand the performance and health status of each device and dehumidifier. When performance degradation, abnormal phenomena, or equipment failures occur, it enables timely designation or modification of operational and maintenance plans, ensuring long-term stable and compliant temperature and humidity within the space (room, workshop) controlled by the dehumidifier; or quickly returning to the set range after anomalies occur, thereby reducing losses caused by temperature and humidity abnormalities. Simultaneously, it saves manpower required for dehumidifier maintenance: replacing on-site inspections (via remote data access) and reducing the manpower required in the control room or data center (through data analysis and digital twin technology providing real-time automatic judgment results).

[0093] Example 2:

[0094] This embodiment is a management system for a dehumidification device, such as... Figure 4 As shown, it includes a data acquisition module 1, a model building module 2, an evaluation module 3, and an interaction module 4 connected in sequence, and also includes a data acquisition module 12, which is connected to the model building module.

[0095] During operation, the data acquisition module acquires first and second historical data from the dehumidifier and sends them to the model building module. The model building module builds a digital twin model, parses and stores the first historical data, processes it, and inputs it into the established digital twin model. It optimizes the digital twin model based on the first and second historical data, and uses the optimized digital twin model to calculate the second real-time data based on the first real-time data. The data acquisition module collects first real-time data from the dehumidifier and inputs it into the model building module. The optimized digital twin model calculates the second real-time data based on the first real-time data. The evaluation module receives the first and second real-time data, evaluates the performance of the dehumidifier based on the data, determines whether the dehumidifier is malfunctioning, and issues an alarm and performs fault diagnosis when an malfunction occurs. The interaction module performs corresponding operations based on the alarm and fault diagnosis prompts from the evaluation module, and stores all data.

[0096] In this embodiment, a display module connected to the interaction module can also be provided to display abnormal alarm indicators and the cause of the fault. Through the display module, maintenance personnel can clearly understand the specific fault and take timely and effective measures to improve efficiency. The display module can be installed on the terminal device or connected to the terminal device.

[0097] The specific manifestations are as follows:

[0098] I. Data Acquisition Module

[0099] The system includes sensor modules, data acquisition devices, and data transmission equipment, as well as edge servers for relaying and preprocessing the initial real-time data. The number and topology of these edge servers depend on the actual physical location. Each data point required by the system corresponds to one output data point from a sensor, such as the supply air temperature. A single sensor device can measure one or more data points, such as a temperature and humidity integrated sensor, which can simultaneously measure the temperature and humidity at a physical location, generating two data points. This invention requires real-time measurement of key operational data, process data, and environmental data of the dehumidification device, such as the temperature and humidity at various key locations in the dehumidification device's piping, the temperature and humidity within the controlled space, the opening degree of each valve in the dehumidification device, the rotational speed of the dehumidification impeller, and the temperature and vibration of each bearing in the fan and motor of the dehumidification device. These data need to be measured using appropriate sensors.

[0100] After data points are measured by sensors, they are collected by a data acquisition device, which converts the continuous measurement results from the sensors into periodic discrete data. The period can be adjusted according to algorithm requirements or other factors. Typically, one sensor device is paired with one data acquisition device, but multiple sensor devices can also share a single data acquisition device. After being collected by the data acquisition device, the data is transmitted through a data transmission device. Generally, data acquisition devices within the same physical space can share a single data transmission device; the specific implementation depends on the conditions of the actual physical space.

[0101] II. Data Acquisition Module

[0102] Obtain the first and second historical data for the dehumidifier. This data can be retrieved from the historical data repository.

[0103] III. Model Building Module

[0104] The model building module is the core of the dehumidification device management system, and it stores several digital twin models of the equipment.

[0105] The operational logic of the model building module is as follows: First, several digital twin models are preset, and then the second real-time data is calculated based on the existing first real-time data using the digital twin models.

[0106] In this embodiment, the established equipment digital twin models include: a digital twin model of a motor, a digital twin model of a fan, a digital twin model of a dehumidifier rotor, a digital twin model of a valve, a digital twin model of a pipeline, and a digital twin model of a heat exchange coil.

[0107] IV. Evaluation Module

[0108] Performance evaluation: The performance of each key component in the dehumidification unit is evaluated, and the overall performance evaluation of the dehumidification unit is obtained based on the operating performance indicators of each component.

[0109] Anomaly alarms and fault diagnosis: Anomaly alarms can be triggered for all data in the model (including first real-time data and second real-time data). The alarm method can be threshold alarm. Fault diagnosis may also require the use of all data in the model.

[0110] A highlight of digital twin models is the ability to calculate other missing data from limited measurement data. This advantage lies in the fact that the model can more comprehensively reflect the object's information, and all of this measured and calculated information can be utilized in performance evaluation, anomaly alarms, and fault diagnosis functions.

[0111] V. Interactive Module

[0112] The system comprises a front-end module and a back-end module. The front-end module primarily interacts with the user, displaying system data in a specific format and acquiring user operation information. Specific front-end module functions include, but are not limited to: user interface functionality, user login and management functions, system overview functions, real-time device data display functions, fault alarm functions, alarm display and management functions, historical data display functions, and system settings functions. The back-end module's main functions are to interact with other components, manage data acquired by each component (including first historical data, second historical data, first real-time data, second real-time data, front-end module input data, etc.), and manage task processes or threads of each component. It serves as the central hub connecting all components. Specific functions include, but are not limited to, data acquisition functions, data storage and management functions, simple data processing functions, and interaction functions with the front-end. The front-end module can be displayed locally on the model building module or remotely on other model building modules via a network. Users can perform settings, control, and other operations on the evaluation module through the front-end module or the front-end module (remotely).

[0113] This invention first establishes digital twin models of each piece of equipment, and then establishes a digital twin model of the entire dehumidification system. Through the digital twin model, performance evaluation, abnormal alarms, and fault diagnosis are provided for each key piece of equipment within the dehumidification system, as well as at the system level. This allows equipment maintenance personnel to understand the performance and health status of the equipment and dehumidification system. When performance degradation, abnormal phenomena, or equipment failures occur, the system can promptly designate or modify operating and maintenance plans, ensuring that the temperature and humidity within the space (room, workshop) controlled by the dehumidification system remain stable and meet requirements in the long term; or, in the event of an anomaly, quickly return the system to the set range, thereby reducing production or storage losses caused by abnormal temperature and humidity.

[0114] On the other hand, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed in the memory, the electronic device can implement the management method of the dehumidification device provided by the above methods, including: acquiring first real-time data of the dehumidification device; inputting the first real-time data into a pre-trained digital twin model, the digital twin model being used to calculate second real-time data of the dehumidification device based on the first real-time data; receiving the first real-time data and the second real-time data, and evaluating the performance of the dehumidification device based on the first real-time data and the second real-time data and determining whether the dehumidification device has malfunctioned; if an malfunction occurs, performing an alarm and fault diagnosis.

[0115] In another aspect, the present invention also provides a computer storage medium storing a computer program, which, when executed on an electronic device, enables the management method of the dehumidification device provided by the above methods, including: acquiring first real-time data of the dehumidification device; inputting the first real-time data into a pre-trained digital twin model, the digital twin model being used to calculate second real-time data of the dehumidification device based on the first real-time data; receiving the first real-time data and the second real-time data, and evaluating the performance of the dehumidification device based on the first real-time data and the second real-time data and determining whether the dehumidification device has malfunctioned; if malfunction occurs, performing an alarm and fault diagnosis.

[0116] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any way. Other variations and modifications may be made without departing from the technical solutions described in the claims.

Claims

1. A management method for a dehumidification device, characterized in that, Includes the following steps: S1: Obtain the first and second historical data of the dehumidifier; S2: Establish a digital twin model and optimize the digital twin model based on the first historical data and the second historical data: The digital twin model calculates the first theoretical data based on the mapping relationship satisfied by the first historical data, and optimizes the digital twin model based on the first theoretical data and the second historical data; S3: Collect real-time operating data or set parameters of the dehumidification device and convert them into discrete first real-time data; input the first real-time data into the optimized digital twin model, and the optimized digital twin model calculates the second real-time data based on the first real-time data and the mapping relationship satisfied by the first real-time data; The second real-time data is data that is difficult to measure in the dehumidification device; S4: Receive the first real-time data and the second real-time data, evaluate the performance of the dehumidification device based on the first real-time data and the second real-time data, and determine whether the dehumidification device is malfunctioning; the determination criteria include whether the relevant calculated values ​​of the first real-time data and the second real-time data meet the third threshold. S5: If an abnormality occurs, an abnormality alarm and fault diagnosis will be performed.

2. The management method of the dehumidification device according to claim 1, characterized in that, The specific steps in step S1 are as follows: S1.1: Measure and record the historical operating data of the dehumidifier; S1.2: Obtain historical operation data from measurement records, and process the historical operation data to obtain the first historical data and the second historical data.

3. The management method of the dehumidification device according to claim 1 or 2, characterized in that, Step S2 specifically includes: S2.1: Map the equipment components, topology, connection relationships, control logic, and physical rules of the dehumidification device to construct physical equations and form a digital twin model; S2.2: Input the first historical data into the digital twin model, and the digital twin model calculates the first theoretical data based on the first historical data; S2.3: Optimize the digital twin model based on the first theoretical data and the second historical data.

4. The management method of the dehumidification device according to claim 1, characterized in that, In step S4, the performance of the dehumidifier is evaluated based on the first real-time data and the second real-time data, and it is determined whether the dehumidifier has malfunctioned. Specifically, this includes: Determine whether the first real-time data meets the first threshold and / or whether the second real-time data meets the second threshold and / or whether the related calculated value of the first real-time data and the second real-time data meets the third threshold; wherein, the first threshold, the second threshold and the third threshold are reference values ​​for the dehumidification device to meet the working performance standards.

5. The management method of a dehumidification device according to claim 1, characterized in that, Step S4 specifically includes: if an abnormality occurs, issuing an abnormality alarm, and performing fault diagnosis based on the first real-time data and the second real-time data at the time of the abnormality alarm.

6. The management method of a dehumidification device according to claim 5, characterized in that, Step S4 also includes displaying an abnormal alarm indicator and the cause of the fault.

7. A management system for a dehumidification device, characterized in that, include: The data acquisition module is used to acquire the first and second historical data of the dehumidifier. The model building module is used to build a digital twin model and optimize the digital twin model based on the first historical data and the second historical data: the digital twin model calculates the first theoretical data based on the mapping relationship satisfied by the first historical data, and optimizes the digital twin model based on the first theoretical data and the second historical data; The data acquisition module is used to acquire the first real-time data of the dehumidification device: acquire the real-time operating data or set parameters of the dehumidification device, and convert them into discrete first real-time data; The first real-time data is then input into the optimized digital twin model, and the optimized digital twin model calculates the second real-time data based on the first real-time data and the mapping relationship satisfied by the first real-time data. The evaluation module receives the first real-time data and the second real-time data, evaluates the performance of the dehumidification device based on the first real-time data and the second real-time data, and determines whether the dehumidification device is malfunctioning. The interaction module is used to perform corresponding operations based on the abnormal alarms and fault diagnosis prompts from the evaluation module.

8. The management system of the dehumidification device according to claim 7, characterized in that, The data acquisition module also includes: The display module, connected to the interaction module, is used to display abnormal alarm indicators and the cause of the fault.

9. An electronic device, characterized in that, The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it causes the electronic device to perform the steps of the management method of the dehumidification device as claimed in any one of claims 1-6.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, which, when executed on an electronic device, implements the steps of the management method of the dehumidification device according to any one of claims 1-6.

Images