Fault diagnosis device for energy storage equipment based on artificial intelligence technology and use method

Abstract

The invention discloses a fault diagnosis device for energy storage equipment based on an artificial intelligence technology and a use method, and relates to the technical field of fault diagnosis of energy storage equipment, the fault diagnosis device comprises an energy storage unit and a fault diagnosis unit, and the energy storage unit comprises an energy storage cabinet, a battery pack, a circuit breaker and a sealing door. According to the invention, the data acquisition unit is used for acquiring the operation data during the operation of the equipment and transmitting the operation data to the microcontroller, the microcontroller transmits the operation data to the central processing unit for analysis and processing, the operation data is compared with the operation data of a normal model, and if the similarity of the two operation data is greater than or equal to a preset value, the central processing unit sends the operation data to the central processing unit. If the similarity of the two items of operation data is smaller than a preset value, the fault state is automatically judged and positioned, the central processing unit transmits the operation data to different fault models, and the fault state is judged and positioned by comparing the similarity probability of the operation data of the fault models and the normal operation data. And the fault type of the energy storage equipment can be obtained according to the similarity probability.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage device fault diagnosis, and in particular to an energy storage device fault diagnosis device based on artificial intelligence technology and a method of using the same. Background Art

[0002] Energy storage equipment plays a vital role in modern power energy systems. With the widespread application of renewable energy and the continuous development of power systems, fault diagnosis of energy storage equipment has become a key issue in the operation, maintenance and management of power systems. The main goal of fault diagnosis and prediction is to timely and accurately detect and judge the fault status of energy storage equipment, facilitate timely maintenance, and thus ensure the reliable operation of the power system.

[0003] The main types of energy storage equipment failures include overcharge / overdischarge, leakage or overheating. Overcharge / overdischarge failures are caused by batteries or supercapacitors exceeding their rated values ​​during charging or discharging. Leakage failures are current leakage caused by equipment insulation damage or humid environment. Overheating failures are caused by increased temperature inside the equipment, which may be due to equipment overload, poor heat dissipation or increased ambient temperature. When diagnosing energy storage equipment failures, most people use detection sensors to detect and diagnose the batteries inside the energy storage equipment in turn to determine whether a failure has occurred. However, in the prior art, since the diagnosis process of energy storage equipment mainly relies on human experience to make judgments, not only is the diagnosis efficiency low, but it also often leads to inaccurate diagnosis, which in turn causes the energy storage equipment to fail to be repaired in a timely manner, causing certain safety hazards. Summary of the invention

[0004] The purpose of the present invention is to provide a fault diagnosis device and a method for use of energy storage equipment based on artificial intelligence technology, which has the advantages of automated diagnosis and high diagnostic efficiency, and solves the problem in the prior art that the energy storage equipment diagnosis process mainly relies on human experience to make judgments, which not only has low diagnostic efficiency but also often leads to inaccurate diagnosis, which in turn causes the energy storage equipment to be unable to be repaired in a timely manner, causing certain safety hazards.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A fault diagnosis device for energy storage equipment based on artificial intelligence technology comprises an energy storage unit and a fault diagnosis unit, wherein the energy storage unit comprises an energy storage cabinet, a battery pack, a circuit breaker and a closed door, wherein the fault diagnosis unit is arranged in the inner cavity of the energy storage cabinet, wherein the fault diagnosis unit comprises a microcontroller, and the microcontroller is installed at the upper end of the inner cavity of the energy storage cabinet, wherein a central processing unit is arranged on the top of the microcontroller, wherein a data acquisition unit is arranged in the inner cavity of the energy storage cabinet, wherein an audible and visual alarm is fixedly connected to one side of the energy storage cabinet, and a display screen is fixedly connected to the front of the closed door, wherein the data acquisition unit is used for collecting equipment operation data, and wherein the data acquisition unit comprises a current sensor, a voltage sensor, a temperature sensor and a humidity sensor, and wherein the central processing unit comprises a data processing module, an analysis model and a database.

[0007] As a further preferred embodiment of the present invention, the closed doors are located on both sides of the front of the energy storage cabinet and are hinged to the energy storage cabinet through hinges, the circuit breaker is installed at the upper end of the inner cavity of the energy storage cabinet, and the battery pack is installed at the lower end of the inner cavity of the energy storage cabinet.

[0008] As a further preferred embodiment of the present invention, a through slot is provided on the top of the energy storage cabinet, and a filter is fixedly connected to the inner cavity of the through slot. A baffle is fixedly connected to the top of the energy storage cabinet, and the baffle is located directly above the through slot.

[0009] As a further preferred embodiment of the present invention, a fan is provided at the bottom of the inner cavity of the energy storage cabinet, an input end of the fan is connected to an output end of the microcontroller, and an input end of the circuit breaker is connected to an output end of the microcontroller.

[0010] As a further preferred embodiment of the present invention, the current sensor and the voltage sensor are both installed on the transmission line of the battery pack, the temperature sensor is installed at the upper end of one side of the inner cavity of the energy storage cabinet, and the humidity sensor is installed at the lower end of one side of the inner cavity of the energy storage cabinet, and the output ends of the current sensor, the voltage sensor, the temperature sensor and the humidity sensor are all connected to the input end of the microcontroller.

[0011] As a further preferred embodiment of the present invention, it also includes a PC end, the data acquisition unit, the microcontroller and the central processing unit are connected in sequence, and the sound and light alarm, the PC end and the display screen are respectively connected to the microcontroller.

[0012] As a further preferred embodiment of the present invention, the data processing module includes a support vector machine algorithm and a recurrent neural network algorithm, and the support vector machine algorithm formula is [f(x)=\text{sign}(\mathbf{w}\cdot\mathbf{x}+b)], wherein f(x) is the predicted output of the input sample x; \mathbf{w} is the normal vector of the hyperplane; \mathbf{x} is the feature vector of the input sample; b is the bias term; \text{sign}(\cdot) is the sign function; the recurrent neural network algorithm formula is [ h^{(t)}=\sigma(W_{hx}x^{(t)}+W_{hh}h^{(t-1)}+b_h)]; where x^{(t)} is the input vector, usually a feature vector or the hidden state of the previous time step, h^{(t-1)} is the hidden state of the previous time step. If t=0, it is usually initialized to a zero vector or a random vector; W_{hx} is the weight matrix input to the hidden layer, W_{hh} is the weight matrix from hidden layer to hidden layer, b_h is the bias vector of the hidden layer, and \sigma is usually a nonlinear activation function.

[0013] A method for using a fault diagnosis device for energy storage equipment comprises the following steps:

[0014] S1. Establishing the analysis model:

[0015] S11. When the energy storage device is operating in normal operation and fault state, the current sensor is used to collect the current data of the battery pack output and input, the voltage sensor is used to collect the output and input voltage data of the battery pack, and the temperature sensor and humidity sensor are used to collect the temperature and humidity data inside the energy storage cabinet;

[0016] S12, after the collection is completed, the current sensor, voltage sensor, temperature sensor and humidity sensor transmit the collected data to the microcontroller, and the microcontroller transmits the data to the central processing unit, and the operation data is processed by the data processing module, mainly storing the operation data under normal operation state through the database, and using the support vector machine to classify the operation data under fault state, forming the operation data under different fault types, and then transmitting it to the database for storage;

[0017] S13, then extracting the operating data of the normal operation in the database, and training it with a recurrent neural network algorithm to obtain a normal model of the device when it is operating normally, and at the same time extracting the operating data of the energy storage device under different fault conditions of the energy storage device in the database, and training it with a recurrent neural network algorithm to obtain a fault model of the energy storage device when it is operating in a fault state, thereby realizing the establishment of an analysis model;

[0018] S2. Perform fault diagnosis on energy storage equipment:

[0019] S21, firstly, using a current sensor and a voltage sensor to collect output and input current and voltage data of the battery pack under operation, and using a temperature sensor and a humidity sensor to collect temperature and humidity data inside the energy storage cabinet, and the collected data will be transmitted to the microcontroller;

[0020] S22, transmitting the data to the central processing unit through the microcontroller, and the central processing unit transmitting the data to the analysis model, by comparing the collected operation data with the operation data of the normal model, if the similarity of the two operation data is greater than or equal to the preset value, it means that the energy storage device is operating normally and there is no fault;

[0021] S23, on the contrary, when the similarity of the two operation data is less than the preset value, the fault state is automatically determined and located, and the central processor transmits the operation data to different fault models, and compares the similarity probability of the operation data of various fault models with the normal operation data, and then obtains the fault type of the energy storage device according to the similarity probability;

[0022] S24. Then the central processor will transmit data and signals to the microcontroller, which will transmit the fault type data to the display screen and PC, so that personnel can check it in time and make corresponding maintenance and prevention work. At the same time, the microcontroller will transmit signals to the sound and light alarm, which will send out sound and light alarms to remind the staff to carry out maintenance in time.

[0023] The present invention has the following beneficial effects:

[0024] The present invention uses a data acquisition unit to collect temperature and humidity data inside the energy storage cabinet and current and voltage data during the output and input of the battery pack when the equipment is running, and the data acquisition unit can transmit the collected operation data to the microcontroller, and the microcontroller will transmit the operation data to the central processing unit for analysis and processing, and compare the operation data with the operation data of the normal model. If the similarity of the two operation data is greater than or equal to the preset value, it means that the equipment is running normally and no fault occurs. When the similarity of the two operation data is less than the preset value, the fault state is automatically determined and located, and the central processing unit will transmit the operation data to different fault models, and by comparing the similarity probabilities of the operation data of various fault models and the normal operation data, the fault type of the energy storage device can be obtained according to the similarity probability, thereby realizing automatic diagnosis, and the fault type data can be transmitted to the microcontroller through the central processing unit, and the microcontroller transmits the fault type data to the display screen and the PC end, so as to facilitate personnel to check in time and make corresponding maintenance and prevention operations, and at the same time, the microcontroller will transmit a signal to the sound and light alarm, and the sound and light alarm will send a sound and light alarm, so as to remind the staff to perform maintenance in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic diagram of the main structure of the present invention;

[0026] Figure 2 It is a schematic diagram of the system principle of the present invention;

[0027] Figure 3 It is a schematic diagram of the process of the present invention;

[0028] Figure 4 It is a schematic diagram of a data acquisition unit of the present invention;

[0029] Figure 5 FIG. 1 is a schematic diagram of a central processing unit of the present invention.

[0030] In the figure: 1. Energy storage unit; 11. Energy storage cabinet; 111. Shielding plate; 112. Fan; 12. Battery pack; 13. Circuit breaker; 14. Closed door; 2. Fault diagnosis unit; 21. Microcontroller; 22. Central processing unit; 23. Data acquisition unit; 24. Sound and light alarm; 25. Display screen. DETAILED DESCRIPTION

[0031] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific preferred embodiments.

[0032] In the description of the present invention, it should be understood that the terms "left side", "right side", "upper part", "lower part" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. "First", "second" and the like do not indicate the importance of the components, and therefore cannot be understood as limiting the present invention. The specific dimensions used in this embodiment are only for illustrating the technical solution, and do not limit the scope of protection of the present invention.

[0033] The energy storage unit 1, energy storage cabinet 11, baffle 111, fan 112, battery pack 12, circuit breaker 13, closed door 14, fault diagnosis unit 2, microcontroller 21, central processing unit 22, data acquisition unit 23, sound and light alarm 24 and display screen 25 of the present invention are all universal standard parts or parts known to those skilled in the art, and their structures and principles can be known to those skilled in the art through technical manuals or through conventional experimental methods.

[0034] Example 1

[0035] like Figure 1-5As shown, it is the first embodiment of the present invention, which provides a fault diagnosis device for energy storage equipment based on artificial intelligence technology, including an energy storage unit 1, the inner cavity of the energy storage cabinet 11 is provided with a fault diagnosis unit 2, the energy storage unit 1 includes the energy storage cabinet 11, a battery pack 12, a circuit breaker 13 and a closed door 14, the fault diagnosis unit 2 includes a microcontroller 21, and the microcontroller 21 is installed at the upper end of the inner cavity of the energy storage cabinet 11, and a central processing unit 22 is arranged on the top of the microcontroller 21, and a data acquisition unit 23 is arranged in the inner cavity of the energy storage cabinet 11, an audible and visual alarm 24 is fixedly connected to the right side of the energy storage cabinet 11, and a display screen 25 is fixedly connected to the front of the closed door 14, the data acquisition unit 23 is used to collect equipment operation data, and the data acquisition unit 23 includes a current sensor, a voltage sensor, a temperature sensor and a humidity sensor, and the central processing unit 22 includes a data processing module, an analysis model and a database.

[0036] like Figure 1-5 As shown, the data acquisition unit 23 is used to collect the temperature and humidity data inside the energy storage cabinet 11 and the current and voltage data of the battery pack 12 during the operation of the equipment, and the data acquisition unit 23 can transmit the collected operation data to the microcontroller 21, and the microcontroller 21 will transmit the operation data to the central processing unit 22 for analysis and processing, and compare the operation data with the operation data of the normal model. If the similarity of the two operation data is greater than or equal to the preset value, it means that the equipment is operating normally and there is no fault. If the similarity of the two operation data is less than the preset value, the fault state is automatically determined and located, and the central processing unit 22 will The operation data is transmitted to different fault models. By comparing the similarity probabilities between the operation data of various fault models and the normal operation data, the fault type of the energy storage equipment can be obtained based on the similarity probability, thereby realizing automated diagnosis. The fault type data can be transmitted to the microcontroller 21 through the central processor 22, and the microcontroller 21 transmits the fault type data to the display screen 25 and the PC, so that personnel can check it in time and make corresponding maintenance and preventive operations. At the same time, the microcontroller 21 will transmit a signal to the sound and light alarm 24, and the sound and light alarm 24 will emit a sound and light alarm to remind the staff to carry out maintenance in time.

[0037] Example 2

[0038] Reference Figure 1 and 2 , which is the second embodiment of the present invention, and this embodiment is based on the previous embodiment.

[0039] In this embodiment, the closed door 14 is located on both sides of the front of the energy storage cabinet 11 and is hinged to the energy storage cabinet 11 through hinges. The circuit breaker 13 is installed at the upper end of the inner cavity of the energy storage cabinet 11, and the battery pack 12 is installed at the lower end of the inner cavity of the energy storage cabinet 11.

[0040] A through slot is provided on the top of the energy storage cabinet 11, and a filter is fixedly connected to the inner cavity of the through slot. A shielding plate 111 is fixedly connected to the top of the energy storage cabinet 11, and the shielding plate 111 is located directly above the through slot.

[0041] A fan 112 is provided at the bottom of the inner cavity of the energy storage cabinet 11 . The input end of the fan 112 is connected to the output end of the microcontroller 21 . The input end of the circuit breaker 13 is connected to the output end of the microcontroller 21 .

[0042] like Figure 1 and 2 As shown, the closed door 14 can be used to close the energy storage cabinet 11, so that the closed door 14 and the energy storage cabinet 11 can ensure the safety of the battery pack 12, the circuit breaker 13, the microcontroller 21 and the central processing unit 22. The through slot on the top of the energy storage cabinet 11 can dissipate heat inside the energy storage cabinet 11, and the shielding plate 111 can shield the through slot to prevent rainwater from dripping in. At the same time, the filter can intercept external impurities. The fan 112 is connected to the microcontroller 21, and then the microcontroller 21 can turn on the fan 112, so that the fan 112 generates airflow to accelerate the air circulation inside the energy storage cabinet 11, which can improve the efficiency of heat dissipation and dehumidification inside the energy storage cabinet 11. The circuit breaker 13 is connected to the microcontroller 21, and then when the equipment fails, the circuit breaker 13 can stop the battery pack 12 from supplying and discharging energy.

[0043] Example 3

[0044] Reference Figure 3-5 , which is the third embodiment of the present invention, and this embodiment is based on the previous two embodiments.

[0045] In this embodiment, the current sensor and the voltage sensor are installed on the transmission line of the battery pack 12, the temperature sensor is installed at the upper end of one side of the inner cavity of the energy storage cabinet 11, and the humidity sensor is installed at the lower end of one side of the inner cavity of the energy storage cabinet 11, and the output ends of the current sensor, the voltage sensor, the temperature sensor and the humidity sensor are all connected to the input end of the microcontroller 21. A PC terminal is also included, and the data acquisition unit 23, the microcontroller 21 and the central processor 22 are connected in sequence, and the sound and light alarm 24, the PC terminal and the display screen 25 are respectively connected to the microcontroller 21.

[0046] The data processing module includes a support vector machine algorithm and a recurrent neural network algorithm. The support vector machine algorithm formula is ([f(x)=\text{sign}(\mathbf{w}\cdot\mathbf{x}+b)]) where (f(x)) is the predicted output of the input sample (x); (\mathbf{w}) is the normal vector of the hyperplane; (\mathbf{x}) is the feature vector of the input sample; (b) is the bias term; (\text{sign}(\cdot)) is the sign function, and the recurrent neural network algorithm formula is [h^{(t)}=\s igma(W_{hx}x^{(t)}+W_{hh}h^{(t-1)}+b_h)], where (x^{(t)}) is the input vector (usually a feature vector or the hidden state of the previous time step), (h^{(t-1)}) is the hidden state of the previous time step (if (t=0), it is usually initialized to a zero vector or a random vector), (W_{hx}) is the weight matrix input to the hidden layer, (W_{hh}) is the weight matrix from hidden layer to hidden layer, (b_h) is the bias vector of the hidden layer, and (\sigma) is usually a nonlinear activation function.

[0047] like Figure 3-5 As shown, the current sensor and the voltage sensor are installed on the transmission line of the battery pack 12, so that when the battery pack 12 is in supply and discharge operation, the current sensor and the voltage sensor can well collect the voltage and current data of the discharge energy supplied by the battery pack 12. The temperature sensor and the humidity sensor are installed on one side of the inner cavity of the energy storage cabinet 11, so as to facilitate the collection of temperature and humidity data inside the energy storage cabinet 11 when the equipment is in operation.

[0048] A method for using a fault diagnosis device for energy storage equipment based on artificial intelligence technology, the method comprising the following steps:

[0049] S1. Establishing the analysis model:

[0050] S11, when the energy storage device is operating in normal operation and fault state, the current data of the output and input of the battery pack 12 is collected by the current sensor, the output and input voltage data of the battery pack 12 is collected by the voltage sensor, and the temperature sensor and humidity sensor are used to collect the temperature and humidity data inside the energy storage cabinet 11;

[0051] S12, after the collection is completed, the current sensor, voltage sensor, temperature sensor and humidity sensor transmit the collected data to the microcontroller 21, and the microcontroller 21 transmits the data to the central processing unit 22, and the operation data is processed by the data processing module, mainly storing the operation data under normal operation state through the database, and using the support vector machine to classify the operation data under fault state, forming the operation data under different fault types, and then transmitting it to the database for storage;

[0052] S13, then extracting the operating data of the normal operation in the database, and training it with a recurrent neural network algorithm to obtain a normal model of the device when it is operating normally, and at the same time extracting the operating data of the energy storage device under different fault conditions of the energy storage device in the database, and training it with a recurrent neural network algorithm to obtain a fault model of the energy storage device when it is operating in a fault state, thereby realizing the establishment of an analysis model;

[0053] S2. Perform fault diagnosis on energy storage equipment:

[0054] S21, firstly, the output and input current and voltage data of the battery pack 12 in the operating state are collected by the current sensor and the voltage sensor, and the temperature and humidity sensor are used to collect the temperature and humidity data inside the energy storage cabinet 11, and the collected data will be transmitted to the microcontroller 21;

[0055] S22, the microcontroller 21 transmits the data to the central processor 22, and the central processor 22 transmits the data to the analysis model, and compares the collected operation data with the operation data of the normal model. If the similarity of the two operation data is greater than or equal to a preset value, it means that the energy storage device operates normally and there is no fault;

[0056] S23, on the contrary, when the similarity of the two operation data is less than the preset value, the fault state is automatically determined and located, and the central processor 22 transmits the operation data to different fault models, and compares the similarity probability of the operation data of various fault models with the normal operation data, and then the fault type of the energy storage device can be obtained according to the similarity probability;

[0057] S24, the central processing unit 22 will then transmit data and signals to the microcontroller 21, and the microcontroller 21 will transmit the fault type data to the display screen 25 and the PC, so that the personnel can check it in time and make corresponding maintenance and prevention operations. At the same time, the microcontroller 21 will transmit signals to the sound and light alarm 24, and the sound and light alarm 24 will emit sound and light alarms to remind the staff to carry out maintenance in time.

[0058] The standard parts used in this application document can all be purchased from the market and can be customized according to the description in the specification and drawings. The specific connection methods of each part adopt conventional means such as mature bolts, rivets, welding, etc. in the prior art. The machinery, parts and equipment all adopt conventional models in the prior art. The control method is automatic control through a controller. The control circuit of the controller can be implemented through simple programming by technicians in this field, which is common knowledge in the field. This application is mainly used to protect mechanical devices, so this application no longer explains the control method and circuit connection in detail.

[0059] The preferred embodiments of the present invention are described in detail above; however, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all belong to the protection scope of the present invention.

Claims

1. A fault diagnosis device for energy storage equipment based on artificial intelligence technology, characterized in that: The invention comprises an energy storage unit (1) and a fault diagnosis unit (2), wherein the energy storage unit (1) comprises an energy storage cabinet (11), a battery pack (12), a circuit breaker (13) and a closed door (14), wherein the fault diagnosis unit (2) is arranged in the inner cavity of the energy storage cabinet (11), wherein the fault diagnosis unit (2) comprises a microcontroller (21), and the microcontroller (21) is installed at the upper end of the inner cavity of the energy storage cabinet (11), and a central processing unit (22) is arranged on the top of the microcontroller (21), and the inner cavity of the energy storage cabinet (11) is provided with a data acquisition unit (23), a sound and light alarm (24) is fixedly connected to one side of the energy storage cabinet (11), and a display screen (25) is fixedly connected to the front of the closed door (14), and the data acquisition unit (23) is used for collecting equipment operation data, and the data acquisition unit (23) comprises a current sensor, a voltage sensor, a temperature sensor and a humidity sensor, and the central processing unit (22) comprises a data processing module, an analysis model and a database.

2. The fault diagnosis device for energy storage equipment based on artificial intelligence technology according to claim 1, characterized in that: The closed door (14) is located on both sides of the front of the energy storage cabinet (11) and is hinged to the energy storage cabinet (11) through hinges. The circuit breaker (13) is installed at the upper end of the inner cavity of the energy storage cabinet (11), and the battery pack (12) is installed at the lower end of the inner cavity of the energy storage cabinet (11).

3. The fault diagnosis device for energy storage equipment based on artificial intelligence technology according to claim 1, characterized in that: A through slot is provided on the top of the energy storage cabinet (11), and a filter is fixedly connected to the inner cavity of the through slot; a shielding plate (111) is fixedly connected to the top of the energy storage cabinet (11), and the shielding plate (111) is located directly above the through slot.

4. The fault diagnosis device for energy storage equipment based on artificial intelligence technology according to claim 1 is characterized in that: A fan (112) is provided at the bottom of the inner cavity of the energy storage cabinet (11), an input end of the fan (112) is connected to an output end of the microcontroller (21), and an input end of the circuit breaker (13) is connected to an output end of the microcontroller (21).

5. The fault diagnosis device for energy storage equipment based on artificial intelligence technology according to claim 1, characterized in that: The current sensor and the voltage sensor are both installed on the transmission line of the battery pack (12), the temperature sensor is installed on the upper end of one side of the inner cavity of the energy storage cabinet (11), and the humidity sensor is installed on the lower end of one side of the inner cavity of the energy storage cabinet (11), and the output ends of the current sensor, the voltage sensor, the temperature sensor, and the humidity sensor are all connected to the input end of the microcontroller (21).

6. The fault diagnosis device for energy storage equipment based on artificial intelligence technology according to claim 1 is characterized in that: It also includes a PC end, wherein the data acquisition unit (23), the microcontroller (21) and the central processing unit (22) are connected in sequence, and the sound and light alarm (24), the PC end and the display screen (25) are respectively connected to the microcontroller (21).

7. The fault diagnosis device for energy storage equipment based on artificial intelligence technology according to claim 1 is characterized in that: The data processing module includes a support vector machine algorithm and a recurrent neural network algorithm. The support vector machine algorithm formula is [f(x)=\text{sign}(\mathbf{w}\cdot\mathbf{x}+b)], where f(x) is the predicted output of the input sample x; \mathbf{w} is the normal vector of the hyperplane; \mathbf{x} is the feature vector of the input sample; b is a bias term; \text{sign}(\cdot) is a sign function; the recurrent neural network algorithm formula is [h^{(t)}=\sigma(W_{hx}x^{(t)}+W_{hh}h^{(t-1)}+b_h)]; where x^{(t)} is the input vector, usually a feature vector or the hidden state of the previous time step, h^{(t-1)} is the hidden state of the previous time step. If t=0, it is usually initialized to a zero vector or a random vector; W_{hx} is the weight matrix input to the hidden layer, W_{hh} is the weight matrix from hidden layer to hidden layer, b_h is the bias vector of the hidden layer, and \sigma is usually a nonlinear activation function.

8. The method for using the fault diagnosis device for energy storage equipment according to any one of claims 1 to 7, characterized in that: The method of use includes the following steps: S1. Establishing the analysis model: S11, when the energy storage device is operating in normal operation and fault state, using a current sensor to collect current data output and input of the battery pack (12), using a voltage sensor to collect voltage data output and input of the battery pack (12), and using a temperature sensor and a humidity sensor to collect temperature and humidity data inside the energy storage cabinet (11); S12, after the collection is completed, the current sensor, the voltage sensor, the temperature sensor and the humidity sensor transmit the collected data to the microcontroller (21), and the microcontroller (21) transmits the data to the central processing unit (22), the operation data is processed by the data processing module, the operation data under normal operation is stored in the database, and the operation data under fault state is classified by the support vector machine to form operation data under different fault types, and then transmitted to the database for storage; S13, then extracting the operating data of the normal operation in the database, and training it with a recurrent neural network algorithm to obtain a normal model of the device when it is operating normally, and at the same time extracting the operating data of the energy storage device under different fault conditions of the energy storage device in the database, and training it with a recurrent neural network algorithm to obtain a fault model of the energy storage device when it is operating in a fault state, thereby realizing the establishment of an analysis model; S2. Perform fault diagnosis on energy storage equipment: S21, firstly, using a current sensor and a voltage sensor to collect output and input current and voltage data of the battery pack (12) in operation, and using a temperature sensor and a humidity sensor to collect temperature and humidity data inside the energy storage cabinet (11), and the collected data will be transmitted to the microcontroller (21); S22, transmitting the data to the central processing unit (22) through the microcontroller (21), and the central processing unit (22) transmitting the data to the analysis model, and comparing the collected operation data with the operation data of the normal model. If the similarity between the two operation data is greater than or equal to a preset value, it means that the energy storage device is operating normally and no fault occurs; S23, on the contrary, when the similarity of the two operation data is less than the preset value, the fault state is automatically determined and located, and the central processor (22) transmits the operation data to different fault models, and by comparing the similarity probabilities of the operation data of various fault models and the normal operation data, the fault type of the energy storage device can be obtained according to the similarity probability; S24, the central processing unit (22) then transmits data and signals to the microcontroller (21), and the microcontroller (21) transmits the fault type data to the display screen (25) and the PC, so that personnel can check the data in time and make corresponding maintenance and preventive operations. At the same time, the microcontroller (21) transmits signals to the sound and light alarm (24), and the sound and light alarm (24) emits sound and light alarms to remind the staff to carry out maintenance in time.

Images